Electronic device and handwriting correction method based on input field of background in electronic device

Abstract

The present document relates to an electronic device, a handwriting correction method based on an input field of a background in the electronic device, and a non-transitory storage medium. The electronic device, according to one embodiment, comprises: a display comprising a touch panel; a memory for storing instructions; and at least one processor. The instructions may be set to, when executed by the at least one processor, instruct the electronic device to: display a background image through the display; when handwriting is inputted to a screen on which the background image is displayed, obtain handwriting text line data by using strokes corresponding to the handwriting input; identify one or more input field regions of the background image on the basis of shapes indicated by one or more paths of the background image; determine respective bounds of the one or more input field regions on the basis of the character size of text present within a specific distance from each of the one or more input field regions; identify an input field region corresponding to the handwriting text line data from among the one or more input field regions on the basis of the respective bounds of the one or more input field regions; identify the type of the input field region on the basis of an input field type determining condition; and correct the handwriting text line data according to a correction method based on the identified type so that the handwriting text line data is contained within the bound of the input field region. Other embodiments are also possible.

Description

Handwriting correction method based on input fields in electronic devices and backgrounds of electronic devices

[0001] The present disclosure relates to an electronic device and a method for correcting handwriting based on an input field of a background in the electronic device.

[0002] With the advancement of digital technology, electronic devices are now available in various forms, such as smartphones, tablet personal computers (PCs), and personal digital assistants (PDAs). Electronic devices are also being developed into wearable devices to enhance portability and accessibility.

[0003] Electronic devices can provide applications for handwriting, recognizing handwriting created by an input module (e.g., a digital pen or mouse) or by the user's hand, and displaying it on a display screen. Handwriting recognition technology can be categorized into two types: one that converts a user's previously written strokes in batches, and the other that updates and provides recognition results as the user writes. Handwriting recognition technology is utilized in a variety of fields, allowing users to convert their handwriting into text and input it into a handwriting application, or utilize technologies such as shape recognition to draw diagrams, for example.

[0004] Recently, handwriting correction technology has been used to improve the aesthetics and readability of a user's handwriting by correcting and adjusting handwriting on a character-by-character, word-by-word, and line-by-line basis. Conventional handwriting correction technology corrects handwriting regardless of its background image. If the background image includes an input field and the user inputs handwriting within that field, the handwriting may be corrected independently of the background image's input field, potentially shifting the handwriting to a location that doesn't align with the input field. This can be inconvenient if the handwriting entered into the background image's input field is shifted to a different location due to handwriting correction.

[0005] The present disclosure provides an electronic device for identifying an input field corresponding to handwriting in a background when handwriting is input on a background image and for correcting the handwriting to fit the input field of the background, and a handwriting correction method based on the input field of the background in the electronic device.

[0006] According to one embodiment of the present disclosure, an electronic device may include a display including a touch panel, a memory storing instructions, and at least one processor. The instructions according to one embodiment, when executed by the at least one processor, may cause the electronic device to display a background image through the display, and, when handwriting is input on a screen on which the background image is displayed, obtain handwriting text line data using strokes corresponding to the handwriting input. The instructions, when executed by the at least one processor, may cause the electronic device to identify at least one input field area of ​​the background image based on a shape indicated by at least one path of the background image. The instructions, when executed by the at least one processor, may cause the electronic device to determine a bound of each of the at least one input field areas based on a font size of text existing within a specified distance from each of the at least one input field areas. The instructions, when executed by the at least one processor, may cause the electronic device to identify an input field area corresponding to the handwritten text line data among the at least one input field area based on a bound of each of the at least one input field area. The instructions, when executed by the at least one processor, may cause the electronic device to identify a type of the input field area based on an input field type determination condition. The instructions, when executed by the at least one processor, may cause the electronic device to correct the handwritten text line data according to a correction method based on the identified type so that the handwritten text line data is included within a bound of the input field area.

[0007] According to one embodiment of the present disclosure, a method for correcting handwriting based on an input field of a background in an electronic device may include an operation of displaying a background image through a display, and, when handwriting is input on a screen on which the background image is displayed, obtaining handwriting text line data using strokes corresponding to the handwriting input. The method may include an operation of identifying at least one input field area of ​​the background image based on a shape indicated by at least one path of the background image. The method may include an operation of determining a bound of each of the at least one input field area based on a font size of text existing within a specified distance from each of the at least one input field area. The method may include an operation of identifying an input field area corresponding to the handwriting text line data among the at least one input field area based on the bound of each of the at least one input field area. The method may include an operation of identifying a type of the input field area based on an input field type determination condition. The method may include an operation of correcting the handwriting text line data according to a correction method based on the identified type such that the handwriting text line data is included within a bound of the input field area.

[0008] In a non-transitory storage medium storing a program according to an embodiment of the present disclosure, the program may include instructions that, when executed by at least one processor of an electronic device, cause the electronic device to display a background image through a display, and, when handwriting is input on a screen on which the background image is displayed, obtain handwriting text line data using strokes corresponding to the handwriting input, identify at least one input field area of ​​the background image based on a shape indicated by at least one path of the background image, determine a bound of each of the at least one input field area based on a font size of text existing within a specified distance from each of the at least one input field area, identify an input field area corresponding to the handwriting text line data among the at least one input field area based on the bound of each of the at least one input field area, identify a type of the input field area based on an input field type determination condition, and correct the handwriting text line data according to a correction method based on the identified type so that the handwriting text line data is included within the bound of the input field area.

[0009] FIG. 1 is a block diagram of an electronic device within a network environment according to various embodiments.

[0010] FIG. 2 is a diagram showing the configuration of an electronic device according to one embodiment.

[0011] FIG. 3 is a diagram illustrating the configuration of a software module of an electronic device according to one embodiment.

[0012] FIG. 4 is a diagram showing the configuration of a UI module, a handwriting data processing module, a background processing module, and a recognition module according to one embodiment.

[0013] FIG. 5 is a flowchart illustrating a handwriting correction operation based on an input field of a background in an electronic device according to one embodiment.

[0014] FIG. 6 is a diagram illustrating an example of obtaining box-shaped input field areas from a background image according to one embodiment.

[0015] FIG. 7 is a diagram illustrating an example of obtaining input field areas in the form of parentheses from a background image according to one embodiment.

[0016] FIG. 8 is a diagram illustrating an example of obtaining input field areas in the form of underlines from a background image according to one embodiment.

[0017] FIG. 9 is a diagram illustrating an example of obtaining input field areas in the form of check boxes from a background image according to one embodiment.

[0018] FIG. 10 is a diagram illustrating an example of obtaining input field areas in single-line and multi-line forms from a background image according to one embodiment.

[0019] Fig. 11 is a drawing showing an example of strokes corresponding to handwriting input according to one embodiment.

[0020] FIG. 12 is a diagram illustrating an example of identifying an input field area corresponding to handwritten text line data among input field areas according to one embodiment.

[0021] FIG. 13 is a diagram illustrating an example of matching each of a plurality of handwritten text line data with each of a plurality of input field areas according to one embodiment.

[0022] FIG. 14 is a diagram illustrating an example of correcting the line slope of handwritten text line data according to one embodiment.

[0023] FIG. 15 is a diagram illustrating an example of correcting line spacing of handwritten text data according to one embodiment.

[0024] FIG. 16 is a diagram illustrating an example of correcting word spacing of handwritten text line data according to one embodiment.

[0025] FIG. 17 is a diagram illustrating an example of correcting letters of handwritten text line data according to one embodiment.

[0026] FIG. 18 is a drawing showing an example of correcting character skew of handwritten text line data according to one embodiment.

[0027] FIG. 19 is a diagram for explaining basic correction and input field-based correction of handwritten text line data according to one embodiment.

[0028] FIG. 20 is a diagram illustrating an example of correcting handwritten text line data based on a single-line input field area according to one embodiment.

[0029] FIG. 21 is a drawing showing an example of correcting handwritten text line data based on a multi-line input field area according to one embodiment.

[0030] FIG. 22 is a drawing showing a character using a descent region according to one embodiment.

[0031] FIG. 23 is a diagram showing an example of correction when handwritten text data includes characters using a descent region according to one embodiment.

[0032] FIG. 24 is a flowchart illustrating a handwriting correction operation based on a background input field according to a candidate correction request according to one embodiment.

[0033] FIG. 25 is a drawing showing an example of a handwriting correction screen based on an input field of a background during candidate correction according to one embodiment.

[0034] FIG. 26 is a flowchart illustrating a handwriting correction operation based on an input field of a background according to an automatic correction request according to one embodiment.

[0035] FIG. 27 is a drawing showing an example of a handwriting correction screen based on an input field of a background during automatic correction according to one embodiment.

[0036] In connection with the description of the drawings, the same or similar reference numerals may be used for identical or similar components.

[0037] Hereinafter, embodiments of the present disclosure will be described in detail with reference to the drawings so that those skilled in the art can easily practice the present disclosure. However, the present disclosure may be implemented in various different forms and is not limited to the embodiments described herein. In connection with the description of the drawings, the same or similar reference numerals may be used for the same or similar components. In addition, in the drawings and related descriptions, descriptions of well-known functions and configurations may be omitted for clarity and conciseness. The term "user" used in the embodiments of the present disclosure may refer to a person using an electronic device or a device (e.g., an artificial intelligence electronic device) using an electronic device.

[0038] FIG. 1 is a block diagram of an electronic device (101) within a network environment (100) according to various embodiments. Referring to FIG. 1, in the network environment (100), the electronic device (101) may communicate with the electronic device (102) via a first network (198) (e.g., a short-range wireless communication network), or may communicate with at least one of the electronic device (104) and the server (108) via a second network (199) (e.g., a long-range wireless communication network). In one embodiment, the electronic device (101) may communicate with the electronic device (104) via the server (108). According to one embodiment, the electronic device (101) may include a processor (120), a memory (130), an input module (150), an audio output module (155), a display module (160), an audio module (170), a sensor module (176), an interface (177), a connection terminal (178), a haptic module (179), a camera module (180), a power management module (188), a battery (189), a communication module (190), a subscriber identification module (196), or an antenna module (197). In some embodiments, the electronic device (101) may omit at least one of these components (e.g., the connection terminal (178)), or may have one or more other components added. In some embodiments, some of these components (e.g., the sensor module (176), the camera module (180), or the antenna module (197)) may be integrated into one component (e.g., the display module (160)).

[0039] The processor (120) may, for example, execute software (e.g., a program (140)) to control at least one other component (e.g., a hardware or software component) of the electronic device (101) connected to the processor (120) and perform various data processing or operations. According to one embodiment, as at least a part of the data processing or operations, the processor (120) may store commands or data received from other components (e.g., a sensor module (176) or a communication module (190)) in a volatile memory (132), process the commands or data stored in the volatile memory (132), and store result data in a non-volatile memory (134). According to one embodiment, the processor (120) may include a main processor (121) (e.g., a central processing unit or an application processor) or an auxiliary processor (123) (e.g., a graphics processing unit, a neural processing unit (NPU), an image signal processor, a sensor hub processor, or a communication processor) that can operate independently or together with the main processor (121). For example, when the electronic device (101) includes the main processor (121) and the auxiliary processor (123), the auxiliary processor (123) may be configured to use less power than the main processor (121) or to be specialized for a given function. The auxiliary processor (123) may be implemented separately from the main processor (121) or as a part thereof.

[0040] The auxiliary processor (123) may control at least a part of functions or states associated with at least one component (e.g., a display module (160), a sensor module (176), or a communication module (190)) of the electronic device (101), for example, on behalf of the main processor (121) while the main processor (121) is in an inactive (e.g., sleep) state, or together with the main processor (121) while the main processor (121) is in an active (e.g., application execution) state. In one embodiment, the auxiliary processor (123) (e.g., an image signal processor or a communication processor) may be implemented as a part of another functionally related component (e.g., a camera module (180) or a communication module (190)). In one embodiment, the auxiliary processor (123) (e.g., a neural network processing unit) may include a hardware structure specialized for processing artificial intelligence models. The artificial intelligence models may be generated through machine learning. This learning can be performed, for example, on the electronic device (101) itself where the artificial intelligence model is executed, or can be performed through a separate server (e.g., server (108)). The learning algorithm can include, for example, supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning, but is not limited to the examples described above. The artificial intelligence model can include multiple artificial neural network layers.The artificial neural network may be one of a deep neural network (DNN), a convolutional neural network (CNN), a recurrent neural network (RNN), a restricted Boltzmann machine (RBM), a deep belief network (DBN), a bidirectional recurrent deep neural network (BRDNN), a deep Q-network, or a combination of two or more of the above, but is not limited to the examples described above. In addition to, or alternatively to, a hardware structure, an artificial intelligence model may include a software structure.

[0041] The memory (130) can store various data used by at least one component (e.g., processor (120) or sensor module (176)) of the electronic device (101). The data can include, for example, software (e.g., program (140)) and input data or output data for commands related thereto. The memory (130) can include volatile memory (132) or non-volatile memory (134).

[0042] The program (140) may be stored as software in the memory (130) and may include, for example, an operating system (142), middleware (144), or an application (146).

[0043] The input module (150) can receive commands or data to be used in a component of the electronic device (101) (e.g., a processor (120)) from an external source (e.g., a user) of the electronic device (101). The input module (150) can include, for example, a microphone, a mouse, a keyboard, a key (e.g., a button), or a digital pen (e.g., a stylus pen).

[0044] The audio output module (155) can output audio signals to the outside of the electronic device (101). The audio output module (155) can include, for example, a speaker or a receiver. The speaker can be used for general purposes, such as multimedia playback or recording playback. The receiver can be used to receive incoming calls. In one embodiment, the receiver can be implemented separately from the speaker or as part of the speaker.

[0045] The display module (160) can visually provide information to an external party (e.g., a user) of the electronic device (101). The display module (160) may include, for example, a display, a holographic device, or a projector and a control circuit for controlling the device. In one embodiment, the display module (160) may include a touch sensor configured to detect a touch, or a pressure sensor configured to measure the intensity of a force generated by the touch.

[0046] The audio module (170) can convert sound into an electrical signal, or vice versa, convert an electrical signal into sound. In one embodiment, the audio module (170) can acquire sound through the input module (150), output sound through the sound output module (155), or an external electronic device (e.g., electronic device (102)) (e.g., speaker or headphone) directly or wirelessly connected to the electronic device (101).

[0047] The sensor module (176) can detect the operating status (e.g., power or temperature) of the electronic device (101) or the external environmental status (e.g., user status) and generate an electrical signal or data value corresponding to the detected status. According to one embodiment, the sensor module (176) can include, for example, a gesture sensor, a gyro sensor, a barometric pressure sensor, a magnetic sensor, an acceleration sensor, a grip sensor, a proximity sensor, a color sensor, an IR (infrared) sensor, a biometric sensor, a temperature sensor, a humidity sensor, or an illuminance sensor.

[0048] The interface (177) may support one or more designated protocols that may be used to directly or wirelessly connect the electronic device (101) to an external electronic device (e.g., the electronic device (102)). In one embodiment, the interface (177) may include, for example, a high definition multimedia interface (HDMI), a universal serial bus (USB) interface, an SD card interface, or an audio interface.

[0049] The connection terminal (178) may include a connector through which the electronic device (101) may be physically connected to an external electronic device (e.g., electronic device (102)). In one embodiment, the connection terminal (178) may include, for example, an HDMI connector, a USB connector, an SD card connector, or an audio connector (e.g., a headphone connector).

[0050] A haptic module (179) can convert electrical signals into mechanical stimuli (e.g., vibration or movement) or electrical stimuli that a user can perceive through tactile or kinesthetic sensations. In one embodiment, the haptic module (179) may include, for example, a motor, a piezoelectric element, or an electrical stimulation device.

[0051] The camera module (180) can capture still images and videos. In one embodiment, the camera module (180) may include one or more lenses, image sensors, image signal processors, or flashes.

[0052] The power management module (188) can manage the power supplied to the electronic device (101). According to one embodiment, the power management module (188) can be implemented as, for example, at least a part of a power management integrated circuit (PMIC).

[0053] A battery (189) may power at least one component of the electronic device (101). In one embodiment, the battery (189) may include, for example, a non-rechargeable primary battery, a rechargeable secondary battery, or a fuel cell.

[0054] The communication module (190) may support the establishment of a direct (e.g., wired) communication channel or a wireless communication channel between the electronic device (101) and an external electronic device (e.g., electronic device (102), electronic device (104), or server (108)), and the performance of communication through the established communication channel. The communication module (190) may operate independently from the processor (120) (e.g., application processor) and may include one or more communication processors that support direct (e.g., wired) communication or wireless communication. According to one embodiment, the communication module (190) may include a wireless communication module (192) (e.g., a cellular communication module, a short-range wireless communication module, or a global navigation satellite system (GNSS) communication module) or a wired communication module (194) (e.g., a local area network (LAN) communication module, or a power line communication module). Among these communication modules, the corresponding communication module can communicate with an external electronic device (104) via a first network (198) (e.g., a short-range communication network such as Bluetooth, wireless fidelity (WiFi) direct, or infrared data association (IrDA)) or a second network (199) (e.g., a long-range communication network such as a legacy cellular network, a 5G network, a next-generation communication network, the Internet, or a computer network (e.g., a LAN or WAN)). These various types of communication modules can be integrated into a single component (e.g., a single chip) or implemented as multiple separate components (e.g., multiple chips). The wireless communication module (192) can verify or authenticate the electronic device (101) within a communication network such as the first network (198) or the second network (199) by using subscriber information (e.g., an international mobile subscriber identity (IMSI)) stored in the subscriber identification module (196).

[0055] The wireless communication module (192) can support 5G networks and next-generation communication technologies following the 4G network, such as NR access technology (new radio access technology). The NR access technology can support high-speed transmission of high-capacity data (eMBB (enhanced mobile broadband)), minimization of terminal power and connection of multiple terminals (mMTC (massive machine type communications)), or high reliability and low latency (URLLC (ultra-reliable and low-latency communications)). The wireless communication module (192) can support, for example, a high-frequency band (e.g., mmWave band) to achieve a high data transmission rate. The wireless communication module (192) can support various technologies for securing performance in a high-frequency band, such as beamforming, massive multiple-input and multiple-output (MIMO), full dimensional MIMO (FD-MIMO), array antenna, analog beam-forming, or large scale antenna. The wireless communication module (192) can support various requirements specified in the electronic device (101), an external electronic device (e.g., the electronic device (104)), or a network system (e.g., the second network (199)). According to one embodiment, the wireless communication module (192) can support a peak data rate (e.g., 20 Gbps or more) for realizing 1eMBB, a loss coverage (e.g., 164 dB or less) for realizing mMTC, or a U-plane latency (e.g., 0.5 ms or less for downlink (DL) and uplink (UL), or 1 ms or less for round trip) for realizing URLLC.

[0056] The antenna module (197) can transmit or receive signals or power to or from an external device (e.g., an external electronic device). In one embodiment, the antenna module (197) may include an antenna including a radiator formed of a conductor or a conductive pattern formed on a substrate (e.g., a PCB). In one embodiment, the antenna module (197) may include a plurality of antennas (e.g., an array antenna). In this case, at least one antenna suitable for a communication method used in a communication network, such as the first network (198) or the second network (199), may be selected from the plurality of antennas, for example, by the communication module (190). A signal or power may be transmitted or received between the communication module (190) and an external electronic device via the at least one selected antenna. In some embodiments, in addition to the radiator, another component (e.g., a radio frequency integrated circuit (RFIC)) may be additionally formed as a part of the antenna module (197).

[0057] According to various embodiments, the antenna module (197) may form a mmWave antenna module. According to one embodiment, the mmWave antenna module may include a printed circuit board, an RFIC disposed on or adjacent to a first side (e.g., a bottom side) of the printed circuit board and capable of supporting a designated high-frequency band (e.g., a mmWave band), and a plurality of antennas (e.g., an array antenna) disposed on or adjacent to a second side (e.g., a top side or a side side) of the printed circuit board and capable of transmitting or receiving signals in the designated high-frequency band.

[0058] At least some of the above components can be interconnected and exchange signals (e.g., commands or data) with each other via a communication method between peripheral devices (e.g., a bus, GPIO (general purpose input and output), SPI (serial peripheral interface), or MIPI (mobile industry processor interface)).

[0059] According to one embodiment, commands or data may be transmitted or received between the electronic device (101) and an external electronic device (104) via a server (108) connected to a second network (199). Each of the external electronic devices (102 or 104) may be the same or a different type of device as the electronic device (101). According to one embodiment, all or part of the operations executed in the electronic device (101) may be executed in one or more of the external electronic devices (102, 104, or 108). For example, when the electronic device (101) is to perform a certain function or service automatically or in response to a request from a user or another device, the electronic device (101) may, instead of or in addition to executing the function or service itself, request one or more external electronic devices to perform the function or at least a part of the service. One or more external electronic devices that receive the request may execute at least a portion of the requested function or service, or an additional function or service related to the request, and transmit the result of the execution to the electronic device (101). The electronic device (101) may process the result as is or additionally and provide it as at least a portion of a response to the request. For this purpose, cloud computing, distributed computing, mobile edge computing (MEC), or client-server computing technology may be used, for example. The electronic device (101) may provide an ultra-low latency service by using distributed computing or mobile edge computing, for example. In another embodiment, the external electronic device (104) may include an Internet of Things (IoT) device. The server (108) may be an intelligent server utilizing machine learning and / or a neural network. According to one embodiment, the external electronic device (104) or the server (108) may be included in the second network (199).The electronic device (101) can be applied to intelligent services (e.g., smart home, smart city, smart car, or healthcare) based on 5G communication technology and IoT-related technology.

[0060] FIG. 2 is a diagram showing the configuration of an electronic device according to one embodiment.

[0061] Referring to FIG. 2, an electronic device according to an embodiment may include a display (260), a processor (220), and a memory (230). The electronic device (201) according to an embodiment is not limited thereto and may further include various components or may be configured by excluding some of the components. According to an embodiment, the electronic device (201) may further include other components necessary for performing handwriting correction based on an input field of a background (e.g., other components described in FIG. 1). The electronic device (201) according to an embodiment may further include all or part of the electronic device (101) illustrated in FIG. 1.

[0062] A display (260) according to an embodiment (e.g., display (160) of FIG. 1) can simultaneously support input / output functions of data, as well as detect touch (and / or proximity) by an external object (e.g., a human body (e.g., a user's finger) or a stylus pen (203)). The display (260) according to an embodiment may include a sensing panel (261) and a display panel (262). According to an embodiment, the sensing panel (261) may form a layer structure with the display panel (262), but may also operate without being included in the display (260).

[0063] According to an embodiment, a sensing panel (261) can detect a position of a touch input of a stylus pen (203), and a display panel (262) can output an image (or screen) (e.g., a background image or a background screen). The display (260) according to an embodiment may further include a driving circuit (not shown) that controls the display panel (262) to output an image through the display panel (262). According to an embodiment, the sensing panel (261) may be configured with an input pad of an EMR (electro-magnetic resonance) method or an EMI (electro-magnetic interface) method using an electromagnetic sensor when the stylus pen (203) supports the EMR (electro-magnetic resonance) method. According to an embodiment, the sensing panel (261) may also be configured with an input pad of an ECR (electrically coupled resonance) method or another method. The input detection method of the sensing panel (261) may not be limited to a specific input detection method. A sensing panel (261) according to an embodiment can receive a magnetic field from a stylus pen (203) and detect the position of the stylus pen (203) therefrom. The sensing panel (261) can be composed of one or more panels that form a mutually layered structure to detect an input using a plurality of sensors. The sensing panel (261) according to an embodiment can be implemented as a touch screen panel (TSP), and if implemented as a touch screen panel, the position of the stylus pen (203) can be identified based on an output signal from an electrode. The stylus pen (203) according to an embodiment can be implemented using an AES (active electrostatic) method, and those skilled in the art will understand that there is no limitation on the type of implementation. The sensing panel (261) according to an embodiment can detect contact or proximity of a human body (e.g., a user's finger) in addition to the stylus pen (203).For example, the sensing panel (261) can detect a handwriting (e.g., handwriting) input by the stylus pen (203) or the user's finger. The sensing panel (361) can generate an input signal corresponding to the handwriting input by the stylus pen (203) or the user's finger and transmit the input signal to the processor (220). According to one embodiment, the sensing panel (261) can transmit strokes (e.g., a set of touch points or touch points at 3 ms intervals (e.g., 120 touch points per second)) to the processor (220) at specified time intervals in response to the handwriting input.

[0064] According to one embodiment, the display panel (262) may receive display data from the processor (320) and display it. For example, the display panel (262) may display an application screen according to the execution of an application (e.g., a note (or handwritten note) application) based on the control of the processor (220), and may display a background image on the application screen. For example, the display panel (262) may display at least one stroke data according to handwriting input by the stylus pen (203) or the user's finger while the background image is displayed based on the control of the processor (220). According to one embodiment, the configuration of the display (260) is merely an example, and the type and number of panels constituting the display (260) and the upper and lower positions of the panels may vary depending on the manufacturing technology of the electronic device (201) (or the electronic device (101) of FIG. 1).

[0065] A processor (220) according to an embodiment (e.g., processor (120) of FIG. 1) may include a circuit for processing, and may include some or all of a central processing unit (CPU), an application processor (AP), a neural processing unit (NPU), and a graphics processing unit (GPU). The processor (220) according to an embodiment may mean at least one processor. The processor (220) according to an embodiment may include a hardware structure (e.g., an AI chip) specialized for processing an artificial intelligence (AI) model. The processor (220) according to an embodiment may perform an overall control operation of the electronic device (201) and may perform at least one operation for performing a handwriting correction method based on an input field of the background of the present disclosure.

[0066] A processor (220) according to an embodiment may display a background image through a display (260). A processor (220) according to an embodiment may execute an application capable of handwriting input (e.g., a note application), select a background image based on user input from among various background images through a menu on an application screen, and display the selected background image on the display (260). A background image according to an embodiment may include various images. A processor (220) according to an embodiment may render a displayable file (or data) into an image and display it as a background image on the lowest layer (or background). For example, a displayable file may include an image of a document file (e.g., a PDF (portable document format) file), a file including a document form such as a contract, a report, meeting minutes, a test paper, a note, or a textbook, or an image file.

[0067] According to one embodiment, a processor (220) can identify a handwriting input (e.g., input by a stylus pen (203)) on a background image displayed through a display (260). According to one embodiment, the processor (220) can display a background image on the lowest layer and receive a handwriting input through a handwriting input layer (or handwriting input layer) that is a layer higher than the background image layer.

[0068] A processor (220) according to one embodiment can identify whether to correct handwriting entered on a background image.

[0069] According to one embodiment, the processor (220) may identify handwriting input on a background image to be corrected based on a real-time (or automatic) correction request or a post-correction request for handwriting. For example, a real-time correction request may be a request to automatically correct handwriting input on a background image in real time (or at a specified time interval or at a specified stroke count). For example, real-time correction may correct handwriting input on a background image in real time based on the completion of a word. For example, real-time correction may perform correction on the first word when a first word is input and a second word is input, at the time of inputting the second word. For example, real-time correction may correct handwriting for a user input after a specified amount of time has elapsed after the user input.

[0070] Post-processing can be done by inputting handwriting on a background image and then correcting the handwriting when the user requests correction.

[0071] In an embodiment, the processor (220) may acquire handwritten text line data using strokes corresponding to handwritten input on the background image when correction (e.g., automatic correction or post-correction) of handwriting input on a background image is required, and may identify (or determine) at least one input field of the background image. In an embodiment, the processor (220) may acquire handwritten text line data after identifying at least one input field area, or may identify at least one input field area after acquiring handwritten text line data, or may perform the identification of at least one input field area and acquisition of handwritten text line data through multi-processing.

[0072] First, an example in which the processor (220) identifies at least one input field of a background image will be described. According to an embodiment, the processor (220) may determine (or identify) at least one input field area based on input field area information provided for the background image, if such information is provided. For example, if the background image is a file (e.g., a PDF file) that provides input field information, the processor (220) may determine the input field area by receiving input field area information included in the file of the background image.

[0073] According to an embodiment, the processor (220) may determine (or identify) at least one input field area of ​​the background image based on a shape indicated by at least one pass of the background image. For example, if a box shape is identified by at least one pass of the background image, the processor (220) may identify an input field area corresponding to the box shape. If an underline shape is identified by at least one pass of the background image, the processor (220) may identify an input field area corresponding to the underline shape. If a bracket shape is identified by at least one pass of the background image, the processor (220) may identify an input field area corresponding to the bracket shape.

[0074] A processor (220) according to one embodiment can perform text recognition on a background image and obtain text information.

[0075] For example, text may mean at least one line of characters containing at least one character (e.g., a letter, symbol, and / or formula). For example, text information may include the size of the text (e.g., the height and / or length of the text), the number of text lines of the text (e.g., one text line or multiple text lines), the size of characters included in the text (e.g., font size), and / or blank spaces between characters included in the text (e.g., blank spaces longer than spaces).

[0076] According to an embodiment, the processor (220) may determine or adjust the bounds (e.g., the positions of the four corners of a rectangle corresponding to the input field area) of at least one input field area using text information about a background image. According to an embodiment, the processor (220) may determine the bounds of each of the at least one input field area based on the font size of text existing within a specified distance from each of the at least one input field areas. For example, when an underscore type input field area is identified and text information of text within a specified distance from the underscore type input field area is acquired, the processor (220) may adjust the bounds of the underscore type input field area so that the vertical length (or height) of the underscore type input field area is longer (or higher) by a specified length (or height) than the vertical length (or height) of the font of the text included in the text. The underscore type input field area may be an input field area having an underline (e.g., “_”) at the bottom of an area where a character or word is to be input to indicate a position where the character or word is to be input.

[0077] For example, when a parenthesis type input field area is identified and text information of text within a specified distance from the parenthesis type input field area is acquired, the processor (220) can adjust the bounds of the parenthesis type input field area so that the vertical length (or height) of the parenthesis type input field area is longer (or higher) by a specified length (or height) than the vertical length (or height) of the font based on the font of the letters included in the text.

[0078] Hereinafter, an example of obtaining handwritten text line data using strokes corresponding to handwriting input on a background image according to an embodiment will be described. The processor (220) may collect strokes (e.g., strokes) corresponding to handwriting input and obtain (or recognize) handwriting data including the strokes corresponding to handwriting input. The processor (220) according to an embodiment may classify the collected strokes into strokes of a handwritten text group and strokes of a handwritten non-text data group through document analyzing of the collected strokes. For example, the strokes of the handwritten text group may be strokes determined to be characters (e.g., characters, symbols, and / or formulas) through document analysis among the collected strokes. For example, the strokes of the handwritten non-text data group may be strokes determined to not be characters (e.g., characters, symbols, and / or formulas) through document analysis among the collected strokes. According to an embodiment, a processor (220) may obtain at least one handwritten text line data (hwrlinedata) using strokes of a handwritten text group. According to an embodiment, a processor (220) may obtain handwritten non-text extra data (hwrextradata) using strokes of a handwritten non-text data group. The handwritten text line data according to an embodiment may refer to data for a character string of one line. The handwritten text line data according to an embodiment may include the number of strokes corresponding to a character string of one line, coordinate information of each stroke corresponding to a character string of one line, and bound information indicating an area of ​​the handwritten text line data (e.g., position information of each vertex of a rectangle indicating an area of ​​the handwritten text line data).In one embodiment, the handwritten non-text extra data may include the number of non-letter strokes, coordinate information for each non-letter stroke, and bound information corresponding to the non-letter strokes (e.g., position information for each corner of a rectangle representing an area of ​​the handwritten non-text extra data).

[0079] A processor (220) according to an embodiment may identify whether an input field area corresponding to handwritten text line data exists among at least one input field area. A processor (220) according to an embodiment may identify an input field area corresponding to handwritten text line data among at least one input field area based on a bound of each of the at least one input field area. A processor (220) according to an embodiment may compare bound information of the handwritten text line data with bound information of each of the at least one input field area, and if an input field area overlapping (or being overlapped with) the handwritten text line data exists among the at least one input field area, the processor (220) may identify the input field area overlapping the handwritten text line data as an input field area corresponding to the handwritten text line data. A processor (220) according to an embodiment may identify (or determine or select) an input field area having a widest overlapping range as an input field area corresponding to the handwritten text line data when handwritten text line data and a plurality of input field areas overlap. In one embodiment, the processor (220) may compare the bound information of the handwritten text line data with the bound of each of at least one input field areas, and if there is no input field area that overlaps with the handwritten text line data among the at least one input field areas, identify (or determine or judge) that there is no input field area corresponding to the handwritten text line data.

[0080] According to an embodiment, the processor (220) may correct the handwritten text line data using a specified correction method (e.g., a basic correction method) based on coordinate information of each stroke of the handwritten text line data regardless of the input field area when there is no input field area corresponding to the handwritten text line data among at least one input field area. According to an embodiment, the basic correction method may include some or all of a plurality of corrections. For example, the plurality of corrections may include line tilt correction, line spacing correction, word spacing correction, letter correction, and / or slant correction. For example, the line tilt correction may be a correction that analyzes the stroke segment of each character of the handwritten text line data to identify reference positions, identifies a line (e.g., a reference line) corresponding to the reference positions, and horizontalizes the characters of the handwritten text line data according to the reference line. Line spacing correction may be a correction that allows handwritten text line data to be included in the space between the top line and the bottom line, while being spaced apart from the top line and the bottom line by a certain space (or interval). Word spacing correction may be a correction that allows the space (or interval) between words in the handwritten text line data to be certain. Letter correction may be a correction that removes unintended serif portions from each letter in the handwritten text line data. Slant correction may be a correction that removes slant from letters. According to an embodiment, the processor (220) may provide an option that allows selection of whether to apply each of a plurality of corrections of a basic correction method, and may activate some or all of the plurality of corrections based on a user selection input through the option.

[0081] According to an embodiment, the processor (220) may identify the type of the input field area corresponding to the handwritten text line data when there is an input field area corresponding to the handwritten text line data among at least one input field area. According to an embodiment, the processor (220) may identify the type of each of at least one input field area included in the background image based on an input field type determination condition, and may identify the type of the input field area corresponding to the handwritten text line data among at least one input field area. For example, the input field type determination condition may include a shape of the input field area, a horizontal length of the input field area, a vertical length of the input field area, a ratio of the horizontal length and the vertical length of the input field area, and / or the number of text lines corresponding to the input field area.

[0082] Table 1 below is a table showing examples of input field types according to one embodiment.

[0083] Type description of input fields Type 1 Unclassified type A given type (e.g., input field type obtained from PDF) Type 2 Single-line box type A box whose width is longer than its height and whose size allows for the input of one line of text Type 3 Multi-line box type A box whose width is longer than its height and whose size allows for the input of multiple lines of text Type 4 Check box type A box whose width and height have a ratio of approximately 1 and whose size allows for the input of simple symbols such as “V” or “O” Type 5 Underscore type An underlined type Type 6 Parentheses type A box that includes a pair of left and right parentheses

[0084] Referring to Table 1 above, the processor (220) according to one embodiment may identify the type of the input field area corresponding to the handwritten text line data as one of the first type (e.g., unclassified type), the second type (e.g., single-line box type), the third type (e.g., multi-line box type), the fourth type (e.g., check box type), the fifth type (e.g., underscore type), or the sixth type (e.g., parenthesis type) based on the input field type determination condition. In one embodiment, the processor (220) may receive input field information included in the file of the background image when the background image is a file providing input field information (e.g., PDF file), determine (or determine or identify) the type of the input field area corresponding to the handwritten text line data as the first type (e.g., unclassified type), and identify the input field area of ​​the unclassified type. According to an embodiment, the processor (220) may determine (or determine or identify) the type of the input field area as a single-line box type if the input field area corresponding to the handwritten text line data is in a box shape, has a horizontal length longer than a vertical length, and has a size that allows one line of text to be input. For example, the processor (220) may identify the interior of the single-line box shape as a single-line type input field area. According to an embodiment, the processor (220) may determine (or determine or identify) the type of the input field area as a multi-line box type if the input field area corresponding to the handwritten text line data is in a box shape, has a horizontal length longer than a vertical length, and has a size that allows multiple lines of text to be input. For example, the processor (220) may identify the interior of the multi-line box shape as a multi-line box type input field area.

[0085] According to one embodiment, the processor (220) may determine (or determine or identify) the type of the input field area as a checkbox type if the input field area corresponding to the handwritten text line data has a box shape with a ratio of width to height of approximately 1 and a size that allows the input of simple symbols such as “V” or “O.” For example, the processor (220) may identify the interior of the checkbox shape as an input field area of ​​the checkbox type.

[0086] According to one embodiment, the processor (220) may determine (or determine or identify) the type of the input field area as an underscore type if the input field area corresponding to the handwritten text line data is in the form of an underline. For example, the processor (220) may identify an area in which the height of the text around the underline is the vertical length and the length of the underline is the horizontal length as an input field area of ​​the underscore type.

[0087] According to one embodiment, the processor (220) may determine (or determine or identify) the type of the input field area as a parenthesis type if the input field area corresponding to the handwritten text line data is in the form of parentheses. For example, the processor (220) may identify an area in which the height of the parenthesis symbol is the vertical length and the length of the space between the parenthesis symbols is the horizontal length as an input field area of ​​the parenthesis type.

[0088] According to one embodiment, the processor (220) can correct handwritten text line data to be included within the bounds of the input field area according to a correction method based on the type of the input field area.

[0089] According to one embodiment, the processor (220) may correct the slope, size, and / or stroke of the handwritten text line data so that the handwritten text line data is included in the input field area of ​​the unclassified type based on bound information (e.g., layout information) of the input field area provided from the background image, if the type of the input field area corresponding to the handwritten text line data is an unclassified type.

[0090] In one embodiment, the processor (220) performs a tilt correction (e.g., a first tilt correction) to horizontally level each character of the handwritten text line data along a bottom line of the input field area of ​​the single-line box type when the type of the input field area corresponding to the handwritten text line data is a single-line box type, and corrects the size of the handwritten text line data tilt-corrected along the bottom line (e.g., a reduction correction) so that the handwritten text line data tilt-corrected along the bottom line is included in the input field area of ​​the single-line box type, or corrects the sizes of strokes included in the handwritten text line data (e.g., a reduction correction).

[0091] According to an embodiment, if the type of the input field area corresponding to the handwritten text line data is a multi-line box type, the processor (220) may perform a tilt correction (e.g., a second tilt correction) to horizontally align each character of the handwritten text line data according to a reference line according to a reference position corresponding to the characters of the handwritten text line data, and may correct the size of the corrected handwritten text line data (e.g., reduction) so that the corrected handwritten text line data is included in the input field area of ​​the multi-line box type, or may correct the sizes of strokes included in the corrected handwritten text line data (e.g., reduction correction). In an embodiment, when the type of an input field area corresponding to handwritten text line data is a multi-line box type and a plurality of handwritten text line data (e.g., first handwritten text line data and second handwritten text line data) exist, the processor (220) may correct each of the first and second handwritten text line data in the same manner as the handwritten text line data (e.g., multi-line box type correction method), and then perform line spacing correction so that the first handwritten text line data and the second handwritten text line data have a constant line spacing (line space). For example, the length of the line spacing may be determined within a range in which the first and second handwritten text line data do not exceed the input field area of ​​the multi-line box type, and may be set to the length of the line spacing of texts within a specified distance from the input field area of ​​the multi-box type.

[0092] In one embodiment, the processor (220) may identify whether the handwritten text data includes a character (e.g., an alphabet) having a descender if the type of the input field area corresponding to the handwritten text line data is an underscore type. For example, a descender may be a portion of an alphabet where a letter of a font extends below a baseline. In one embodiment, the processor (220) may perform a slope correction to horizontalize each character of the handwritten text line data according to the underline of the input field area of ​​the underscore type if the type of the input field area corresponding to the handwritten text line data is an underscore type and the handwritten text data does not include a character having a descender, and may reduce the size of the corrected handwritten text line data according to the underline so that the handwritten text line data that has been slope-corrected according to the underline is included in the input field area of ​​the underscore type or may perform a correction to reduce the sizes of strokes included in the handwritten text line data. In one embodiment, the processor (220) may perform a tilt correction (e.g., a third tilt correction) to horizontally level each character of the handwritten text line data according to the underline of the input field area of ​​the underscore type when the type of the input field area corresponding to the handwritten text line data is an underscore type and the handwritten text data includes characters having descenders, and may perform a correction to move the position of the corrected handwritten text line data or move the positions of strokes included in the handwritten text line data so that descender portions of the characters of the corrected handwritten text line data are placed below the underline, and may perform a correction to reduce the size of the corrected handwritten text line data or reduce the sizes of strokes included in the handwritten text line data so that the corrected handwritten text line data is included in the input field area of ​​the underscore type.

[0093] A memory (230) according to an embodiment (e.g., memory (130) of FIG. 1) may include one or more storage media for storing instructions. A memory (230) according to an embodiment may store various data used by at least one component (e.g., processor (220) and / or display (260)) of an electronic device (201). The data may include, for example, software (e.g., software module or program (140)) and input data or output data for commands related thereto. A memory (230) according to an embodiment may store a program (e.g., software or program (140) of FIG. 1) for performing handwriting correction, as well as various data generated during program execution. A memory (230) according to an embodiment may store commands (or instructions) for causing a processor (220) to perform a handwriting correction operation (or method) based on an input field of the background of the present disclosure.

[0094] An electronic device (e.g., the electronic device (101) of FIG. 1 or the electronic device (201) of FIG. 2) according to an embodiment of the present disclosure may include a display including a touch panel (e.g., the display module (160) of FIG. 1 or the display (260) of FIG. 2), a memory (e.g., the memory (130) of FIG. 1 or the memory (230) of FIG. 2)) for storing instructions, and at least one processor (e.g., the processor (120) of FIG. 1 or the processor (220) of FIG. 2). The instructions according to an embodiment, when executed by the at least one processor, may cause the electronic device to display a background image through the display, and obtain handwriting text line data using strokes corresponding to handwriting input when handwriting is input on a screen on which the background image is displayed. The instructions, when executed by the at least one processor, may cause the electronic device to obtain handwriting text line data based on a shape indicated by at least one path of the background image. The instructions may be configured to identify at least one input field area of ​​a background image. The instructions, when executed by the at least one processor, may cause the electronic device to determine a bound of each of the at least one input field area based on a font size of text existing within a specified distance from each of the at least one input field area. The instructions, when executed by the at least one processor, may cause the electronic device to identify an input field area corresponding to the handwritten text line data among the at least one input field area based on the bound of each of the at least one input field area. The instructions, when executed by the at least one processor, may cause the electronic device to identify a type of the input field area based on an input field type determination condition.The instructions, when executed by the at least one processor, may cause the electronic device to correct the handwritten text line data according to a correction method based on the identified type so that the handwritten text line data is contained within the bounds of the input field area.

[0095] The input field type determination conditions according to one embodiment may include the shape of the input field area, the horizontal length of the input field area, the vertical length of the input field area, the ratio of the horizontal length and the vertical length of the input field area, and / or the number of text lines corresponding to the input field area.

[0096] The instructions according to one embodiment, when executed by the at least one processor, may cause the electronic device to identify the type of the input field area corresponding to the handwritten text line data as one of an unclassified type, a single-line box type, a multi-line box type, a check box type, an underscore type, or a parenthesis type based on the input field type determination condition.

[0097] The instructions according to one embodiment, when executed by the at least one processor, may cause the electronic device to perform a first tilt correction to horizontally align each character of the handwritten text line data along a bottom line of the input field area of ​​the single-line box type according to a single-line box type correction method when the identified type is the single-line box type, and to correct a size of the handwritten text line data or a size of a stroke of the handwritten text line data so that the first tilt-corrected handwritten text line data is included within the input field area of ​​the single-line box type.

[0098] The instructions according to one embodiment, when executed by the at least one processor, may cause the electronic device to perform a second tilt correction to horizontally align each character of the handwritten text line data according to a multi-line box type correction method according to a reference line corresponding to the characters of the handwritten text line data when the identified type is the multi-line box type, and to correct a size of the handwritten text line data or a size of a stroke of the handwritten text line data so that the second tilt-corrected handwritten text line data is included within an input field area of ​​the multi-line box type.

[0099] The instructions according to one embodiment, when executed by the at least one processor, may cause the electronic device to correct the first handwritten text line data and the second handwritten text line data according to a correction method based on the multi-line box type when the identified type is the multi-line box type and the first handwritten text line data and the second handwritten text line data correspond to an input field area of ​​the multi-line box type, and to perform line spacing correction so that the first handwritten text line data and the second handwritten text line data have a designated line spacing.

[0100] The instructions according to one embodiment, when executed by the at least one processor, may cause the electronic device to perform a third tilt correction to horizontally align each character of the handwritten text line data along an under line of an input field area of ​​the underscore type according to a correction method based on the underscore type when the identified type is the underscore type and the handwritten text data includes characters having the descender portion, and to move a position of the third corrected handwritten text line data or a position of strokes included in the handwritten text line data such that the descender portion of the characters of the third tilt-corrected handwritten text line data is disposed below the under line.

[0101] The instructions according to one embodiment, when executed by the at least one processor, may cause the electronic device to correct the handwritten text line data based on a basic correction method if an input field area corresponding to the handwritten text line data among the at least one input field area is not identified.

[0102] The basic correction method according to one embodiment may include line tilt correction, line spacing correction, word spacing correction, letter correction and / or skew correction.

[0103] The instructions according to one embodiment, when executed by the at least one processor, may cause the electronic device to perform document analyzing on strokes corresponding to the handwriting input to obtain text group data and non-text group data from the strokes corresponding to the handwriting input, and to perform text recognition on the text group data to obtain the handwriting text line data.

[0104] FIG. 3 is a diagram showing the configuration of a software module of an electronic device according to one embodiment.

[0105] Referring to FIG. 3, an electronic device (201) according to an embodiment may include a software module (300) (e.g., the program (140) of FIG. 1) for executing handwriting correction based on an input field of a background. A memory (230) (e.g., the memory (130) of FIG. 1) of the electronic device (201) may store commands (e.g., instructions) to implement the software module (300) illustrated in FIG. 3. At least one processor (220) may execute the commands stored in the memory (230) to implement the software module (300) illustrated in FIG. 3, and control hardware (e.g., the display module (160) of FIG. 1 or the display (260) of FIG. 2) associated with a function of the software module (300).

[0106] A software module (300) according to one embodiment may include a user interface (UI) module (310), a handwriting data processing module (320), a background processing module (330), and a recognition module (340). At least a portion of the software module (300) may be preloaded on the electronic device (201) or may be downloadable from a server (e.g., server (108)).

[0107] A UI module (310) according to one embodiment may display views containing data associated with a handwriting correction operation based on an input field of a background. The UI module (310) according to one embodiment may display views resulting from application execution on the display (260), and may display a background image and handwriting input by a user through the views.

[0108] A handwriting data processing module (320) according to one embodiment may collect strokes corresponding to handwriting input and obtain handwriting text data (e.g., handwriting line data) using the strokes corresponding to the handwriting input. A handwriting data processing module (320) according to one embodiment may correct the handwriting text data so that it is included in an input field area.

[0109] A background processing module (320) according to one embodiment can extract at least one path and at least one text from a background image and identify at least one input field area of ​​the background image based on the at least one path and at least one text.

[0110] A recognition module (340) according to one embodiment can extract (or recognize) at least one text included in a background image. A recognition module (340) according to one embodiment can obtain (or recognize) handwritten text data (e.g., handwritten line data) using strokes corresponding to handwritten input.

[0111] FIG. 4 is a diagram showing the configuration of a UI module, a handwriting data processing module, a background processing module, and a recognition module according to one embodiment.

[0112] Referring to FIG. 4, a UI module (310) according to an embodiment may include a note composition module (411) and a handwriting engine module (415). The note composition module (411) according to an embodiment may include a view module (412) that configures a note application screen view. The view module (412) may include a foreground view module (413) and a background view module (414). The foreground view module (413) may output a view that displays handwriting according to handwriting input. The background view module (414) may output a view that displays a background image. The background view module (414) may display a view in which a background image (object) is inserted based on a touch input, and the foreground view module (413) may provide touch points according to drawing using a user's body or a stylus pen (203) to a stroke drawing module (416).

[0113] A handwriting engine module (415) according to one embodiment may include a stroke drawing module (416) and a page cache (417). The stroke drawing module (416) may collect strokes corresponding to handwriting input by drawing using the user's body or stylus pen (203) through a view provided by the foreground view module (413). The page cache (417) may temporarily store strokes corresponding to handwriting input for each collected page.

[0114] A handwriting data processing module (320) according to an embodiment may classify strokes collected in response to handwriting input into strokes of a handwriting text group and strokes of a handwriting non-text data group (nontext group) through document analysis and text recognition of the collected strokes. For example, strokes of a handwriting text group may be strokes determined to be letters (e.g., letters, symbols, and / or formulas) through document analysis among the collected strokes. For example, strokes of a handwriting non-text data group may be strokes determined to not be letters (e.g., letters, symbols, and / or formulas) through document analysis among the collected strokes. A handwriting data processing module (320) according to an embodiment may obtain at least one piece of handwriting text line data (hwrlinedata) using strokes of a handwriting text group. The handwriting text line data may mean a character string of one line. A processor (220) according to an embodiment may obtain handwritten non-text extra data (hwrextradata) using strokes of a group of handwritten non-text data. The handwritten text line data according to an embodiment may include the number of strokes of a character string of one line, coordinate information of each stroke of the handwritten text line data, and bound information indicating an area of ​​the handwritten text line data (e.g., position information of each vertex of a rectangle indicating an area of ​​the handwritten text line data). The handwritten non-text extra data according to an embodiment may include the number of non-letter strokes, coordinate information of each non-letter stroke, and bound information corresponding to the non-letter strokes (e.g., position information of each vertex of a rectangle indicating an area of ​​the handwritten non-text extra data). The handwritten data processing module (320) according to an embodiment may perform automatic correction or post-correction on handwritten text data.A handwriting data processing module (320) according to an embodiment may include a post-correction module (421), a handwriting data cache (423), and an automatic correction module (425). The handwriting data cache (423) according to an embodiment may store handwriting data for strokes collected in response to handwriting input and handwriting data recognition results obtained through document analysis and text recognition. For example, the handwriting data cache (423) according to an embodiment may store handwriting text line data and handwriting non-text extra data. The automatic correction module (425) according to an embodiment may obtain handwriting text line data from the handwriting data cache (423) in real time or automatically and request the recognition module (340) to perform handwriting correction based on the input field of the background. According to one embodiment, the candidate correction module (421) may obtain handwritten text line data previously stored in the handwritten data cache (423) based on a user request and request the recognition module (340) to perform handwritten correction based on the input field of the background.

[0115] A background processing module (330) according to one embodiment can render a displayable file (or data) into an image and display it as a background image in the lowest layer (or background view). For example, the displayable file may include an image of a document file (e.g., a portable document format (PDF) file), a file including a document form such as a contract, a report, meeting minutes, a question paper, or a teaching material, or an image file. For example, the background processing module (330) includes a PDF module (431) and can render a PDF file into an image through the PDF module (431).

[0116] A recognition module (340) according to an embodiment may include an integrated recognition requester (441), a document analysis module (442), a text recognition module (443), a shape recognition module (444), a handwriting data beautification module (445), a letter beautification module (446), an input field analysis module (447), and / or a PDF document analysis module (448). A recognition module (340) according to an embodiment may operate using at least one of an integrated recognition requester (441), a document analysis module (442), a text recognition module (443), a shape recognition module (444), a handwriting data beautification module (445), a letter beautification module (446), an input field analysis module (447), and / or a PDF document analysis module (448).

[0117] The recognition module (340) according to one embodiment can identify at least one input field from a background image output through the background view (414). The recognition module (340) according to one embodiment can determine (or identify) at least one input field area based on input field area information provided for the background image, if such information is available. The recognition module (340) according to one embodiment can determine (or identify) at least one input field area of ​​the background image based on a shape indicated by at least one path of the background image.

[0118] A recognition module (340) according to an embodiment may perform text recognition on a background image and obtain text information. The recognition module (340) according to an embodiment may use the text information on the background image to determine or adjust the bounds of at least one input field area (e.g., the positions of four corners of a rectangle corresponding to the input field area).

[0119] A recognition module (340) according to one embodiment can identify whether there is an input field area corresponding to handwritten text line data among at least one input field area.

[0120] According to one embodiment, the recognition module (340) can correct handwritten text line data using a specified correction method (e.g., a basic correction method) at a position based on coordinate information of each stroke of the handwritten text line data, regardless of the input field area, if there is no input field area corresponding to the handwritten text line data among at least one input field area.

[0121] According to one embodiment, the recognition module (340) can identify the type of the input field area corresponding to the handwritten text line data when there is an input field area corresponding to the handwritten text line data among at least one input field area.

[0122] A recognition module (340) according to one embodiment can correct handwritten text line data to be included within the bounds of an input field area according to a correction method based on the type of the input field area.

[0123] According to an embodiment, the recognition module (340) may correct the slope, size, and / or stroke of the handwritten text line data so that the handwritten text line data is included in the input field area of ​​the unclassified type based on bound information (e.g., layout information) of the input field area provided from the background image, if the type of the input field area corresponding to the handwritten text line data is an unclassified type.

[0124] According to an embodiment, the recognition module (340) performs a tilt correction (e.g., a first tilt correction) to horizontally level each character of the handwritten text line data along a bottom line of the input field area of ​​the single-line box type when the type of the input field area corresponding to the handwritten text line data is a single-line box type, and corrects the size of the handwritten text line data tilt-corrected along the bottom line (e.g., a reduction correction) so that the handwritten text line data tilt-corrected along the bottom line is included in the input field area of ​​the single-line box type, or corrects the sizes of strokes included in the handwritten text line data (e.g., a reduction correction).

[0125] According to an embodiment, the recognition module (340) performs a tilt correction (e.g., second tilt correction) to horizontally align each character of the handwritten text line data according to a reference line according to a reference position corresponding to the characters of the handwritten text line data when the type of the input field area corresponding to the handwritten text line data is a multi-line box type, and corrects the size of the corrected handwritten text line data (e.g., reduction) so that the corrected handwritten text line data is included in the input field area of ​​the multi-line box type, or corrects the sizes of strokes included in the corrected handwritten text line data (e.g., reduction correction). In an embodiment, when the type of the input field area corresponding to the handwritten text line data is a multi-line box type and there are a plurality of handwritten text line data (e.g., first handwritten text line data and second handwritten text line data), the recognition module (340) may correct each of the first and second handwritten text line data in the same manner as the handwritten text line data (e.g., multi-line box type correction method), and then perform line spacing correction so that the first handwritten text line data and the second handwritten text line data have a constant line spacing (line space). For example, the length of the line spacing may be determined within a range in which the first and second handwritten text line data do not exceed the input field area of ​​the multi-line box type, and may be set to the length of the line spacing of texts within a specified distance from the input field area of ​​the multi-box type.

[0126] In one embodiment, the recognition module (340) may identify whether the handwritten text data includes a character (e.g., an alphabet) having a descender if the type of the input field area corresponding to the handwritten text line data is an underscore type. For example, a descender may be a portion of an alphabet where a letter of a font extends below a baseline. In one embodiment, the recognition module (340) may perform a slope correction to horizontalize each character of the handwritten text line data according to the underline of the input field area of ​​the underscore type if the type of the input field area corresponding to the handwritten text line data is an underscore type and the handwritten text data does not include a character having a descender, and may reduce the size of the corrected handwritten text line data according to the underline so that the handwritten text line data is included in the input field area of ​​the underscore type or may perform a correction to reduce the sizes of strokes included in the handwritten text line data. In an embodiment, the recognition module (340) performs a tilt correction (e.g., a third tilt correction) to horizontally level each character of the handwritten text line data according to the underline of the input field area of ​​the underscore type when the type of the input field area corresponding to the handwritten text line data is an underscore type and the handwritten text data includes characters having descenders, and moves the position of the corrected handwritten text line data or moves the positions of the strokes included in the handwritten text line data so that the descender portions of the characters of the corrected handwritten text line data are placed below the underline, and reduces the size of the corrected handwritten text line data or reduces the sizes of the strokes included in the handwritten text line data so that the corrected handwritten text line data is included in the input field area of ​​the underscore type.

[0127] An integrated recognition requester (441) according to an embodiment can correct handwritten text line data using a document analysis module (442), a text recognition module (443), a shape recognition module (444), a handwriting data beautification module (445), and / or a letter beautification module (446). The document analysis module (442) according to an embodiment can perform document analyzing on collected strokes to obtain (or recognize) handwritten text line data (hwrlinedata). The shape recognition module (444) according to an embodiment can classify what shape the handwriting extra data (hwrextradata) is when the handwriting extra data (hwrextradata) is obtained. A handwriting data beautification module (445) according to an embodiment may perform line slant correction, line spacing correction, and word spacing correction on handwriting text line data. A letter beautification module (446) according to an embodiment may perform letter correction and / or slant correction on letters included in handwriting text line data. An input field analysis module (447) according to an embodiment may identify at least one input field area from a background image, and identify the type of each of at least one input field areas.

[0128] FIG. 5 is a flowchart illustrating a handwriting correction operation based on an input field of a background in an electronic device according to one embodiment.

[0129] Referring to FIG. 5, a processor (e.g., processor (120) of FIG. 1 or processor (220) of FIG. 2, hereinafter, processor (220) of FIG. 2 will be described as an example) of an electronic device (e.g., electronic device (101) of FIG. 1 or electronic device (201) of FIG. 2) according to one embodiment may perform at least one operation from operations 510 to 560.

[0130] In operation 510, the processor (220) according to an embodiment may obtain handwritten text line data using strokes corresponding to handwritten input on a background image displayed through the display (260). The processor (220) according to an embodiment may execute an application capable of handwritten input (e.g., a note application), select a background image based on user input from among various background images through a menu on the application screen, and display the selected background image on the display (260). The background image according to an embodiment may include various images. The processor (220) according to an embodiment may render a displayable file (or data) into an image and display it as a background image on the lowest layer (or background). For example, the displayable file may include a document file (e.g., a PDF (portable document format) file), a file including a document form such as a contract, a report, meeting minutes, a test paper, a note, a survey, or a textbook, or an image file. According to an embodiment, a processor (220) may identify a handwriting input (e.g., input by a stylus pen (203)) on a background image. According to an embodiment, the processor (220) may collect strokes (e.g., strokes) corresponding to the handwriting input and obtain (or recognize) handwriting data including the strokes corresponding to the handwriting input. According to an embodiment, the processor (220) may identify strokes of a handwriting text group among the collected strokes through document analyzing of the collected strokes. For example, the strokes of the handwriting text group may be strokes determined to be characters (e.g., letters, symbols, and / or formulas) through document analysis among the collected strokes. According to an embodiment, the processor (220) may obtain at least one handwriting text line data (hwrlinedata) using the strokes of the handwriting text group.Handwritten text line data may refer to a line of characters. According to one embodiment, the handwritten text line data may include the number of strokes in the line of characters, coordinate information of each stroke of the handwritten text line data, and bound information indicating an area of ​​the handwritten text line data (e.g., position information of each vertex of a rectangle indicating an area of ​​the handwritten text line data).

[0131] In operation 520, the processor (220) according to one embodiment may determine at least one input field area of ​​the background image based on a shape indicated by at least one pass of the background image. For example, if a box shape is identified by at least one pass of the background image, the processor (220) may identify an input field area corresponding to the box shape. If an underline shape is identified by at least one pass of the background image, the processor (220) may identify an input field area corresponding to the underline shape. If a bracket shape is identified by at least one pass of the background image, the processor (220) may identify an input field area corresponding to the bracket shape. If input field area information is provided for the background image, the processor (220) according to one embodiment may determine (or identify) at least one input field area based on input field area information. For example, if the background image is a file (e.g., a PDF file) that provides input field information, the processor (220) may determine the input field area by receiving input field area information included in the file of the background image.

[0132] In operation 530, the processor (220) according to one embodiment may determine the bounds of each of at least one input field area based on the font size of text existing within a specified distance from each of at least one input field area. For example, when an underscore type input field area is identified and text information of text within a specified distance from the underscore type input field area is acquired, the processor (220) may determine the bounds of the underscore type input field area so that the vertical length (or height) of the underscore type input field area is longer (or higher) by the specified length (or height) than the vertical length (or height) of the font of the letters included in the text. For example, when a parenthesis type input field area is identified and text information of text within a specified distance from the parenthesis type input field area is acquired, the processor (220) may determine the bounds of the parenthesis type input field area so that the vertical length (or height) of the parenthesis type input field area is longer (or higher) by a specified length (or height) than the vertical length (or height) of the font of the letters included in the text.

[0133] In operation 540, the processor (220) according to an embodiment may identify an input field area corresponding to handwritten text line data among at least one input field area based on a bound of each of at least one input field area. The processor (220) according to an embodiment may compare bound information of the handwritten text line data with bound information of each of the at least one input field area, and if there is an input field area overlapping (or being overlapped with) the handwritten text line data among the at least one input field area, the processor (220) may identify the input field area overlapping the handwritten text line data as an input field area corresponding to the handwritten text line data. If the handwritten text line data and a plurality of input field areas overlap, the processor (220) according to an embodiment may identify (or determine or select) an input field area having a widest overlapping range as an input field area corresponding to the handwritten text line data. In one embodiment, the processor (220) may compare the bound information of the handwritten text line data with the bound of each of at least one input field areas, and if there is no input field area that overlaps with the handwritten text line data among the at least one input field areas, identify (or determine or judge) that there is no input field area corresponding to the handwritten text line data.

[0134] In operation 550, the processor (220) according to an embodiment may identify the type of an input field area corresponding to handwritten text line data based on an input field type determination condition. The processor (220) according to an embodiment may identify the type of each of at least one input field area included in a background image based on the input field type determination condition, and may identify the type of an input field area corresponding to handwritten text line data among the at least one input field area. For example, the input field type determination condition may include a shape of the input field area, a horizontal length of the input field area, a vertical length of the input field area, a ratio of the horizontal length and the vertical length of the input field area, and / or a number of text lines corresponding to the input field area. According to an embodiment, the processor (220) may identify the type of the input field area corresponding to the handwritten text line data as one of the first type (e.g., unclassified type), the second type (e.g., single-line box type), the third type (e.g., multi-line box type), the fourth type (e.g., check box type), the fifth type (e.g., underscore type), or the sixth type (e.g., parentheses type) based on the input field type determination condition. If the background image is a file (e.g., a PDF file) that provides input field information, the processor (220) according to an embodiment may receive input field information included in the file of the background image and determine (or determine or identify) the type of the input field area corresponding to the handwritten text line data as the first type (e.g., unclassified type). If the input field area corresponding to the handwritten text line data has a box-shaped horizontal length longer than its vertical length and has a size that allows one line of text input, the processor (220) may determine (or determine or identify) the type of the input field area as the single-line box type.According to an embodiment, the processor (220) may determine (or determine or identify) the type of the input field area as a multi-line box type if the input field area corresponding to the handwritten text line data has a box-shaped width longer than its height and a size that allows multiple lines of text to be input. According to an embodiment, the processor (220) may determine (or determine or identify) the type of the input field area as a checkbox type if the input field area corresponding to the handwritten text line data has a box-shaped width-to-height ratio of approximately 1 and a size that allows simple symbols such as “V” or “O” to be input. According to an embodiment, the processor (220) may determine (or determine or identify) the type of the input field area as an underscore type if the input field area corresponding to the handwritten text line data has an underline type. According to an embodiment, the processor (220) may determine (or determine or identify) the type of the input field area as a parenthesis type if the input field area corresponding to the handwritten text line data has a parenthesis type.

[0135] In operation 560, the processor (220) according to one embodiment may correct the handwritten text line data according to a correction method based on the identified type so that the handwritten text line data is included within the bounds of the input field area. The processor (220) according to one embodiment may correct the size of letters included in the handwritten text line data according to the correction method based on the identified type so that the size of letters included in the handwritten text line data is the same as or similar to the size of letters of text around the input field area (e.g., within a specified distance).

[0136] According to one embodiment, the processor (220) may correct the slope, size, and / or stroke of the handwritten text line data so that the handwritten text line data is included in the input field area of ​​the unclassified type based on bound information (e.g., layout information) of the input field area provided from the background image, if the type of the input field area corresponding to the handwritten text line data is an unclassified type.

[0137] In one embodiment, the processor (220) performs a tilt correction (e.g., a first tilt correction) to horizontally level each character of the handwritten text line data along a bottom line of the input field area of ​​the single-line box type when the type of the input field area corresponding to the handwritten text line data is a single-line box type, and corrects the size of the handwritten text line data tilt-corrected along the bottom line (e.g., a reduction correction) so that the handwritten text line data tilt-corrected along the bottom line is included in the input field area of ​​the single-line box type, or corrects the sizes of strokes included in the handwritten text line data (e.g., a reduction correction).

[0138] According to an embodiment, if the type of the input field area corresponding to the handwritten text line data is a multi-line box type, the processor (220) may perform a tilt correction (e.g., a second tilt correction) to horizontally align each character of the handwritten text line data according to a reference line according to a reference position corresponding to the characters of the handwritten text line data, and may correct the size of the corrected handwritten text line data (e.g., reduction) so that the corrected handwritten text line data is included in the input field area of ​​the multi-line box type, or may correct the sizes of strokes included in the corrected handwritten text line data (e.g., reduction correction). In an embodiment, when the type of the input field area corresponding to handwritten text line data is a multi-line box type and a plurality of handwritten text line data (e.g., first handwritten text line data and second handwritten text line data) exist, the processor (220) may correct each of the first and second handwritten text line data using a multi-line box type correction method, and then perform line spacing correction so that the first handwritten text line data and the second handwritten text line data have a constant line spacing (line space). For example, the length of the line spacing may be determined within a range in which the first and second handwritten text line data do not exceed the input field area of ​​the multi-line box type, and may be set to the length of the line spacing of texts within a specified distance from the input field area of ​​the multi-box type.

[0139] In one embodiment, the processor (220) may identify whether the handwritten text data includes a character (e.g., an alphabet) having a descender if the type of the input field area corresponding to the handwritten text line data is an underscore type. For example, a descender may be a portion of an alphabet where a letter of a font extends below a baseline. In one embodiment, the processor (220) may perform a slope correction (e.g., a third slope correction) to horizontalize each character of the handwritten text line data according to the underline of the input field area of ​​the underscore type if the type of the input field area corresponding to the handwritten text line data is an underscore type and the handwritten text data does not include a character having a descender, and may correct the size of the corrected handwritten text line data (e.g., a reduction correction) so that the handwritten text line data that has been slope-corrected according to the underline is included in the input field area of ​​the underscore type, or may correct the sizes of strokes included in the handwritten text line data (e.g., a reduction correction).In an embodiment, the processor (220) performs a tilt correction (e.g., a third tilt correction) to horizontally level each character of the handwritten text line data according to the underline of the input field area of ​​the underscore type when the type of the input field area corresponding to the handwritten text line data is an underscore type and the handwritten text data includes characters having descenders, moves the position of the corrected handwritten text line data so that the descender portions of the characters of the corrected handwritten text line data are placed below the underline, or performs a correction to move the positions of the strokes included in the handwritten text line data, and corrects the size of the corrected handwritten text line data (e.g., a reduction correction) so that the corrected handwritten text line data is included in the input field area of ​​the underscore type or corrects the sizes of the strokes included in the handwritten text line data (e.g., a reduction correction). According to one embodiment, the processor (220) may correct handwritten text line data using a specified correction method (e.g., a basic correction method) regardless of the input field area when there is no input field area corresponding to handwritten text data among at least one input field area. According to one embodiment, the basic correction method may include a plurality of corrections. For example, the plurality of corrections may include line slant correction, line spacing correction, word spacing correction, letter correction, and / or slant correction.

[0140] According to one embodiment, the processor (220) may correct the size of letters included in the handwritten text line data to be the same as or similar to the size of letters in the surroundings of the input field area (e.g., within a specified distance) according to a correction method based on the type of the input field area so that the handwritten text line data is included within the bounds of the input field area.

[0141] According to an embodiment of the present disclosure, a method for correcting handwriting based on a background input field in an electronic device (e.g., the electronic device 101 of FIG. 1 or the electronic device 201 of FIG. 2) may include an operation of displaying a background image through a display, and, when handwriting is input on a screen on which the background image is displayed, obtaining handwriting text line data using strokes corresponding to the handwriting input. The method may include an operation of identifying at least one input field area of ​​the background image based on a shape indicated by at least one path of the background image. The method may include an operation of determining a bound of each of the at least one input field areas based on a font size of text existing within a specified distance from each of the at least one input field areas. The method may include an operation of identifying an input field area corresponding to the handwriting text line data among the at least one input field area based on the bound of each of the at least one input field areas. The method may include an operation of identifying a type of the input field area based on an input field type determination condition. The method may include an operation of correcting the handwritten text line data according to a correction method based on the identified type so that the handwritten text line data is included within the bounds of the input field area.

[0142] The input field type determination conditions according to one embodiment may include the shape of the input field area, the horizontal length of the input field area, the vertical length of the input field area, the ratio of the horizontal length and the vertical length of the input field area, and / or the number of text lines corresponding to the input field area.

[0143] The method according to one embodiment may include an operation of identifying the type of the input field area corresponding to the handwritten text line data as one of an unclassified type, a single-line box type, a multi-line box type, a check box type, an underscore type, or a parenthesis type based on the input field type determination condition.

[0144] The method according to one embodiment may include, when the identified type is the single-line box type, performing a first tilt correction to horizontally align each character of the handwritten text line data according to a single-line box type correction method along a bottom line of the input field area of ​​the single-line box type, and correcting a size of the handwritten text line data or a size of a stroke of the handwritten text line data so that the first tilt-corrected handwritten text line data is included within the input field area of ​​the single-line box type.

[0145] The method according to one embodiment may include, when the identified type is the multi-line box type, performing a second tilt correction to horizontally align each character of the handwritten text line data according to a multi-line box type correction method with a reference line corresponding to the characters of the handwritten text line data, and correcting a size of the handwritten text line data or a size of a stroke of the handwritten text line data so that the second tilt-corrected handwritten text line data is included within an input field area of ​​the multi-line box type.

[0146] The method according to one embodiment may include an operation of correcting the first handwritten text line data and the second handwritten text line data according to a correction method based on the multi-line box type when the identified type is the multi-line box type and the first handwritten text line data and the second handwritten text line data correspond to an input field area of ​​the multi-line box type, and performing line spacing correction so that the first handwritten text line data and the second handwritten text line data have a designated line spacing.

[0147] The method according to one embodiment may include performing a third tilt correction to horizontally level each of the letters of the handwritten text line data along an under line of an input field area of ​​the underscore type according to a correction method based on the underscore type when the identified type is the underscore type and the handwritten text data includes letters having the descender portion, and performing a correction to move a position of the third corrected handwritten text line data or a position of strokes included in the handwritten text line data so that the descender portion of the letters of the third tilt-corrected handwritten text line data is placed below the under line.

[0148] The method according to one embodiment includes an operation of correcting the handwritten text line data based on a basic correction method if an input field area corresponding to the handwritten text line data among the at least one input field area is not identified, wherein the basic correction method may include line tilt correction, line spacing correction, word spacing correction, letter correction, and / or slant correction.

[0149] According to one embodiment, the method may include an operation of performing document analyzing on strokes corresponding to the handwriting input to obtain text group data and non-text group data from the strokes corresponding to the handwriting input. The method may include an operation of performing text recognition on the text group data to obtain the handwriting text line data.

[0150] FIG. 6 is a diagram illustrating an example of obtaining box-shaped input field areas from a background image according to one embodiment.

[0151] Referring to FIG. 6, a processor (220) according to an embodiment may perform an operation of recognizing at least one path from a background image (600) (e.g., a note image). The processor (220) according to an embodiment may obtain a vector image corresponding to the background image (600) and obtain a plurality of paths (e.g., horizontal line paths or vertical line paths) representing virtual lines representing the outline of the vector image. The processor (220) according to an embodiment may identify a plurality of box shapes using the plurality of paths, and if each of the box shapes is a box shape having a horizontal length longer than a vertical length and a size in which one line of text can be input, the processor (220) may obtain a plurality of single-line input field areas (610) corresponding to the box shapes having a horizontal length longer than a vertical length and a size in which one line of text can be input. The area sizes of the plurality of single-line input field areas (610) may vary depending on the horizontal and vertical lengths of each of the box shapes.

[0152] FIG. 7 is a diagram illustrating an example of obtaining input field areas in the form of parentheses from a background image according to one embodiment.

[0153] Referring to FIG. 7, a processor (220) according to an embodiment may perform an operation of recognizing at least one path from a background image (700) (e.g., a contract image). The processor (220) according to an embodiment may extract paths from the background image (700). The processor (220) according to an embodiment may obtain a vector image corresponding to the background image (700), extract paths representing virtual lines representing the outline of the vector image, and identify parenthesis shapes (e.g., a first parenthesis shape (701) and a second parenthesis shape (703)) using the paths. For example, the parenthesis shape may be a shape including a pair of a left parenthesis and a right parenthesis. According to one embodiment, the processor (220) can identify at least one text (e.g., “gold,” “expedition,” “ / ,” “gold,” “expedition is paid and received at the time of contract. Recipient,” “person”) from the background image (700) and obtain text information corresponding to the at least one text. For example, the text information may include the size of the text (e.g., the height and / or length of the text), the text line corresponding to the text (e.g., one text line or multiple text lines), the size of characters included in the text (e.g., a font size), and / or blank spaces between texts (e.g., blank spaces longer than spaces). The processor (220) according to one embodiment may determine a bound corresponding to the first parenthesis shape (701) using the text information (e.g., the character sizes of “expedition” and “ / ”) of the first parenthesis shape (701) and the text (e.g., “expedition”, “ / ”) within a specified distance from the first parenthesis shape (701) and identify the parenthesis type input field area (711) corresponding to the first parenthesis shape (701). The processor (220) according to one embodiment may determine a bound corresponding to the first parenthesis shape (701) using the text information (e.g., the character sizes of “expedition” and “ / ”) of the second parenthesis shape (703) and the text (e.g., Text information (e.g. "Expedition is paid and received at the time of contract. Recipient", "person") of "Expedition is paid and received at the time of contract.By using the font size of "in" and "number", the bound corresponding to the second parenthesis form (703) can be determined and the parenthesis type input field area (713) corresponding to the second parenthesis form (703) can be identified.

[0154] FIG. 8 is a diagram illustrating an example of obtaining input field areas in the form of underlines from a background image according to one embodiment.

[0155] Referring to FIG. 8, a processor (220) according to an embodiment may perform an operation of recognizing at least one path from a background image (800) (e.g., a document form image). The processor (220) according to an embodiment may obtain a vector image corresponding to the background image (800), extract paths representing virtual lines representing the outline of the vector image, and identify a plurality of underline shapes (801, 802, 803, 804, 805, 806) using the paths. The processor (220) according to an embodiment may identify at least one text (e.g., "Doc Number RXQ", "Date of Record", "BFY", "Vender Number", "Vender Name") from the background image (800) and obtain text information corresponding to the at least one text. For example, the text information may include the size of the text (e.g., the height and / or length of the text), the text line corresponding to the text (e.g., one text line or multiple text lines), the size of the characters included in the text (e.g., the font size), and / or the blank space between the texts (e.g., the blank space longer than the spacing). In one embodiment, the processor (220) uses the text information of the underline shapes (801, 802, 803, 804, 805, 806) and the text within a specified distance from each underline shape (e.g., "Doc Number RXQ", "Date of Record", "BFY", "Vender Number", "Vender Name") to determine the bounds of each of the underline shapes (801, 802, 803, 804, 805, 806) and the underline shapes (801, 802, 803, 804, 805, 806) Each corresponding underscore type input field area (811, 812, 813, 814, 815, 816) can be identified.

[0156] FIG. 9 is a drawing showing an example of obtaining input field areas in the form of check boxes from a background image according to one embodiment.

[0157] Referring to FIG. 9, a processor (220) according to an embodiment may perform an operation of recognizing at least one path from a background image (900) (e.g., a survey image). The processor (220) according to an embodiment may obtain a vector image corresponding to the background image (900), extract paths representing virtual lines representing the outline of the vector image, and identify a plurality (e.g., eight) box shapes (901, 902, 903, 904, 905, 906, 907, 908) using the paths. According to an embodiment, the processor (220) can identify that the box shapes (901, 902, 903, 904, 905, 906, 907, 908) are check box types based on the fact that each of the box shapes has a ratio of width to height that is almost the same or about 1 and a size that allows input of simple symbols such as “V” or “O.” According to an embodiment, the processor (220) can identify at least one text (e.g., “The teacher creates and maintains a learning environment in which all students are actively engaged”, “Maintains a classroom in which my child feels physically and emotionally safe”, “The teacher has high expectations and help my child reach them”, “Yes”, “Sometimes”, “No”, “Not Sure”) from the background image (900) and obtain text information corresponding to the at least one text. For example, text information may include the size of the text (e.g., the height and / or length of the text), the text line corresponding to the text (e.g., one text line or multiple text lines), the size of characters included in the text (e.g., font size), and / or blank spaces between texts (e.g., blank spaces longer than spaces).According to one embodiment, a processor (220) can determine the bound of each check box shape using eight check box shapes and text information of text within a specified distance from each check box shape, and identify input field areas (911, 912, 913, 914, 915, 916, 917, 918) of the check box type.

[0158] FIG. 10 is a diagram illustrating an example of obtaining input field areas in single-line and multi-line forms from a background image according to one embodiment.

[0159] Referring to FIG. 10, a processor (220) according to an embodiment may perform an operation of recognizing at least one path from a background image (1000) (e.g., an event participation form image). The processor (220) according to an embodiment may obtain a vector image corresponding to the background image (1000), extract paths representing virtual lines representing the outline of the vector image, and identify a plurality of box shapes (1001, 1002, 1003, 1004, 1005) using the extracted paths.

[0160] According to an embodiment, a processor (220) can identify whether box shapes (1001, 1002, 1003, 1004, 1005) are single-line shapes and multi-line shapes. According to an embodiment, a processor (220) can identify single-line box shapes (1012, 1014, 1016, 1018) among box shapes (1001, 1002, 1003, 1004, 1005), which are box shapes in which the horizontal length is longer than the vertical length and in which a single line of text can be input. According to an embodiment, a processor (220) can identify multi-line box shapes (1020), which are box shapes in which the horizontal length is longer than the vertical length and in which a plurality of lines of text can be input. In one embodiment, the processor (220) may identify at least one text (e.g., "Participant's full name", "Participant's membership number", "N / A", "Age at start of event", "Unit name", "Please provide details of any disabilities, health or access needs (including allergies) that are relevant to this event") from the background image (1000) and obtain text information corresponding to each of the at least one text. For example, the text information may include a size of the text (e.g., a height and / or a length of the text), a text line corresponding to the text (e.g., a single text line or multiple text lines), a size of characters included in the text (e.g., a font size), and / or a blank space between texts (e.g., a blank space longer than a space).A processor (220) according to one embodiment determines a bound corresponding to each of the single-line box shapes (1001, 1002, 1003, 1004) and the multi-line box shape (1005) by using text information of text within a specified distance from each of the single-line box shapes (1001, 1002, 1003, 1004) and the multi-line box shape (1005), and generates single-line box type input field areas (1012, 1014, 1016, 1018) corresponding to the single-line box shapes (1001, 1002, 1003, 1004) and a multi-line box type input field area (1020) corresponding to the multi-line box shape. Can be identified.

[0161] Fig. 11 is a drawing showing an example of strokes corresponding to handwriting input according to one embodiment.

[0162] Referring to FIG. 11, a processor (220) according to an embodiment may collect (or acquire) strokes (1110, 1112, 1121, 1122, 1113) corresponding to handwriting input based on handwriting input on a background image (1100). The processor (220) according to an embodiment may classify the collected strokes (1110, 1112, 1121, 1122, 1113) corresponding to handwriting input into strokes (1121, 1122) of a handwriting text group and strokes (1110, 1112, 1113) of a handwriting nontext data group through document analyzing. For example, the strokes of the handwritten text group may be strokes that are determined to be characters (e.g., characters, symbols, and / or formulas) through document analysis among the collected strokes. For example, the strokes of the handwritten non-text data group may be strokes that are determined to not be characters (e.g., characters, symbols, and / or formulas) through document analysis among the collected strokes. The processor (220) according to one embodiment may obtain at least one handwritten text line data corresponding to the strokes (1121, 1122) of the handwritten text group and at least one handwritten extra data (hwrextradata) corresponding to the strokes (1110, 1112, 1113) of the handwritten non-text data group. The handwritten text line data according to one embodiment may mean data for a character string of one line (or at least one word). According to one embodiment, handwritten text line data may include the number of strokes corresponding to a line of characters, coordinate information of each stroke corresponding to a line of characters, and bound information indicating an area of ​​the handwritten text line data (e.g., position information of each vertex of a rectangle indicating an area of ​​the handwritten text line data).Handwritten non-text extra data according to an embodiment may include the number of non-letter strokes, coordinate information of each non-letter stroke, and bound information corresponding to the non-letter strokes (e.g., position information of each vertex of a rectangle representing an area of ​​the handwritten non-text extra data). Table 2 below may represent at least one handwritten text line data (hwrlinedata) corresponding to strokes (1121, 1122) of a handwritten text group according to an embodiment, and at least one handwritten extra data (hwrextradata) corresponding to strokes (1110, 1112, 1113) of a handwritten non-text data group.

[0163] Group dataHandwritten text group 1st handwritten text line data (HwrLineData1) - Number of strokes: 25, coordinate information of each stroke, Bound: 177.0, 1304.2, 1850.1, 1600.0 2nd handwritten text data (HwrLineData2) - Number of strokes: 13, coordinate information of each stroke, Bound: 348.8, 1681.6, 1683.3, 1938.9 Handwritten non-text data group 1st handwritten non-text extra data (HwrExtraData1) - Number of strokes: 1, coordinate information of stroke, Bound: 319.4, 401.3, 582.2, 662.5 2nd handwritten non-text extra data (HwrExtraData2) - Number of strokes: 1, Stroke coordinate information, Bound: 715.3, 630.1, 1109.4, 924.1 Third handwriting non-text extra data (HwrExtraData3) - Number of strokes: 1, , Stroke coordinate information, Bound: 274.5, 1880.3, 1708.2, 1903.3

[0164] Referring to Table 2 above, the first handwritten text line data corresponding to the first strokes (1121) according to one embodiment may include the number of strokes of 25, coordinate information of each stroke, and bound information of “177.0, 1304.2, 1850.1, 1600.0”. The second handwritten text line data corresponding to the second strokes (1122) according to one embodiment may include the number of strokes of 13, coordinate information of each stroke, and bound information of “348.8, 1681.6, 1683.3, 1938.9”. The first handwritten non-text extra data corresponding to the third strokes (1110) according to one embodiment may include the number of strokes of 1, coordinate information of the stroke, and bound information of “319.4, 401.3, 582.2, 662.5”. The second handwritten non-text extra data corresponding to the fourth strokes (1112) according to one embodiment may include the number of strokes, coordinate information of the strokes, and bound information of “715.3, 630.1, 1109.4, 924.1”. The third handwritten non-text extra data corresponding to the fifth strokes (1113) according to one embodiment may include the number of strokes, coordinate information of the strokes, and bound information of “274.5, 1880.3, 1708.2, 1903.3”. FIG. 12 is a diagram illustrating an example of identifying an input field area corresponding to handwritten text data among input field areas according to one embodiment.

[0165] Referring to FIG. 12, a processor (220) according to an embodiment may compare the bound information of handwritten text line data (1250) with the bound information of each of the single-line box type input field areas (1210, 1220, 1230) identified from the background image (1200) to identify (or determine or select) the single-line box type input field area (1220) that overlaps the handwritten text line data (1250) among the single-line box type input field areas (1210, 1220, 1230) as the input field area corresponding to the handwritten text line data (1250). In one embodiment, when there are multiple single-line box type input field areas (1210, 1220) overlapping with handwritten text line data (1250), the processor (220) may identify (or determine or select) the input field area (1220) with the widest overlapping range as the single-line box type input field area corresponding to the handwritten text line data (1250). For example, when the handwritten text line data (1250) overlaps with a first single-line box type input field area (1210) by about 30%, overlaps with a second single-line box type input field area (1220) by about 70%, and overlaps with a third single-line box type input field area (1230) by about 0%, the processor (220) may identify the second single-line box type input field area (1220) as the input field area corresponding to the handwritten text line data (1250). According to one embodiment, a processor (220) may determine an input field area based on the position of the first letter (or stroke) of the handwritten text line data (1250) when there are a plurality of single-line box type input field areas (1210, 1220) overlapping with the handwritten text line data (1250).For example, if the first character (or stroke) of the handwritten text line data (1250) is in the second single-line box type input field area (1220), the processor (220) may identify the single-line box type input field area corresponding to the handwritten text line data (1250) as the second input field area (1220).

[0166] FIG. 13 is a diagram illustrating an example of matching each of a plurality of handwritten text line data with each of a plurality of input field areas according to one embodiment.

[0167] Referring to FIG. 13, a processor (220) according to one embodiment may collect (or acquire) strokes (1301, 1302, 1303, 1304, 1305, 1306, 1307) corresponding to handwriting input based on handwriting input in a background image (1300) (e.g., a flight account input form image). According to one embodiment, a processor (220) may obtain handwritten text line data (1310, 1320, 1330, 1340, 1350, 1360, 1370) corresponding to strokes (1301, 1302, 1303, 1304, 1305, 1306, 1307) corresponding to handwritten input through document analyzing of strokes (1301, 1302, 1303, 1304, 1305, 1306, 1307) corresponding to handwritten input. According to one embodiment, a processor (220) may identify (or determine or select) input field areas (1311, 1321, 1331, 1341, 1351, 1361, 1371) overlapping with each of handwritten text line data (1310, 1320, 1330, 1340, 1350, 1360, 1370) as input field areas (1311, 1321, 1331, 1341, 1351, 1361, 1371) corresponding to each of handwritten text line data (1310, 1320, 1330, 1340, 1350, 1360, 1370).

[0168] FIG. 14 is a diagram illustrating an example of correcting the line slope of handwritten text line data according to one embodiment.

[0169] Referring to FIG. 14, a processor (220) according to an embodiment can obtain recognition information at the line, word, and letter levels for handwritten text line data (1400) through document analysis, and can analyze stroke segments of each character of the handwritten text line data (1400) to extract reference positions of each character and identify reference lines (1401) corresponding to the reference positions. The processor (220) according to an embodiment can obtain line slope-corrected handwritten text line data (1410) by correcting distortion of characters of the handwritten text line data (1400) so that the reference line (1401) becomes a horizontal line (1411).

[0170] FIG. 15 is a diagram illustrating an example of correcting line spacing of handwritten text line data according to one embodiment.

[0171] Referring to FIG. 15, a processor (220) according to an embodiment can identify reference lines (e.g., 1511, 1512, 1513, 1514, 1515, 1516, 1517, 1518, 1519, 1520, 1521) of each of the plurality of handwritten text line data when the text includes a plurality of handwritten text line data (1500) through document analysis. According to an embodiment, a processor (220) may perform line spacing correction so that each of a plurality of reference lines (e.g., 1511, 1512, 1513, 1514, 1515, 1516, 1517, 1518, 1519, 1520, 1521) of a plurality of handwritten text line data (1500) has equal spacing. According to an embodiment, the processor (220) may perform line spacing correction during post-correction.

[0172] FIG. 16 is a diagram illustrating an example of correcting word spacing of handwritten text line data according to one embodiment.

[0173] Referring to FIG. 16, a processor (220) according to an embodiment can obtain word-level recognition information for handwritten text line data (1610) through document analysis. The processor (220) according to an embodiment can identify gaps (1611, 1612, 1613, 1614, 1615, 1616, 1617) between words included in the handwritten text line data (1610). According to one embodiment, a processor (220) may perform word spacing correction to change the spacing between words (1611, 1612, 1613, 1614, 1615, 1616, 1617) included in handwritten text line data (1610) to constant spacing (1621, 1622, 1623, 1624, 1625, 1626, 1627) to obtain word spacing-corrected handwritten text line data (1620).

[0174] FIG. 17 is a diagram illustrating an example of correcting letters of handwritten text line data according to one embodiment.

[0175] Referring to FIG. 17, a processor (220) according to an embodiment may obtain letter-level recognition information for handwritten text line data (1710) through document analysis. The processor (220) according to an embodiment may identify unintended serif portions (1711, 1713) in each of the letters included in the handwritten text line data (1710). The processor (220) according to an embodiment may perform letter correction to remove the serif portions (1711, 1713) included in the handwritten text line data (1710) to obtain handwritten text line data (1720) in which the serif portions are corrected (1721, 1723).

[0176] FIG. 18 is a drawing showing an example of correcting character skew of handwritten text line data according to one embodiment.

[0177] Referring to FIG. 18, a processor (220) according to an embodiment may obtain letter-level recognition information for handwritten text line data (1810) through document analysis, and identify slanted strokes in which strokes included in each letter in the handwritten text line data (1810) are written so that the slant is not constant like the original strokes according to the linguistic characteristics of the letter. The processor (220) according to an embodiment may perform slant correction so that the slant is constant for each letter, and obtain corrected handwritten text line data (1820). For example, the processor (220) may identify slanted strokes in which strokes (1801) of the letter 'ㅂ' are written so that the slant is not constant like the original 'ㅂ' strokes according to the linguistic characteristics of the letter. According to one embodiment, the processor (220) can correct (1811) the slant of the stroke (1801) of the letter 'ㅂ' so that the slant is constant like the original 'ㅂ' stroke according to the linguistic characteristics of the letter. As another example, the processor (220) can identify a slant in which the stroke (1802) of the letter 'ㅎ' is written so that the slant is not constant like the original 'ㅎ' stroke according to the linguistic characteristics of the letter. According to one embodiment, the processor (220) can correct (1812) the slant of the stroke (1802) of the letter 'ㅎ' so that the slant is constant like the original 'ㅎ' stroke according to the linguistic characteristics of the letter. Of course, slant correction can also be performed for other letters.

[0178] FIG. 19 is a diagram for explaining basic correction of handwritten text line data and correction based on the type of an input field area according to one embodiment.

[0179] Referring to FIG. 19, a processor (220) according to an embodiment may obtain first handwritten text line data (1912) and second handwritten text line data (1914) based on handwriting input on a background image (1900). If an input field area (1901) (e.g., a single-line box type input field area) corresponding to the first handwritten text line data (1912) exists and an input field area corresponding to the second handwritten text line data (1914) does not exist, the processor (220) according to an embodiment may perform correction based on the single-line box type input field area (1901) for the first handwritten text line data (1912) and perform correction using a basic correction method for the second handwritten text line data (1914). According to an embodiment, the processor (220) may perform a tilt correction (e.g., a first tilt correction) on the first handwritten text line data (1912) to horizontally align each character of the first handwritten text line data (1912) along a bottom line of a single-line box type input field area (1901), and may correct the size of the first handwritten text line data (1912) tilt-corrected along the bottom line (e.g., a reduction correction) so that the first handwritten text line data (1912) tilt-corrected along the bottom line is included in the single-line box type input field area (1901), or may correct the sizes of strokes included in the first handwritten text line data (1912) (e.g., a reduction correction). According to an embodiment, the processor (220) may display the corrected first handwritten text line data (1922) based on the single-line box type input field area (1901).

[0180] According to an embodiment, the processor (220) may include line slant correction, line spacing correction, word spacing correction, letter correction, and / or slant correction for the second handwritten text line data (1914) according to a basic correction method. According to an embodiment, the processor (220) may display the second handwritten text line data (1924) corrected according to the basic correction method.

[0181] FIG. 20 is a drawing showing an example of correcting handwritten text line data based on an input field area of ​​a single-line box type according to one embodiment.

[0182] Referring to FIG. 20, when a single-line box type input field area (2010) corresponding to handwritten text line data (2012) is identified, a processor (220) according to an embodiment may perform a tilt correction (e.g., a first tilt correction) to horizontally level the handwritten text line data (2012) along a bottom line (2001) of the single-line box type input field area (2010), and may correct the size of the handwritten text line data (2012) tilt-corrected along the bottom line (e.g., a reduction correction) or correct the sizes of strokes included in the handwritten text line data (2012) along the bottom line so that the handwritten text line data (2012) tilt-corrected along the bottom line is included within the single-line box type input field area (2010). A processor (220) according to one embodiment may display handwritten text line data (2014) corrected to be included in a single line box type input field area (2010).

[0183] FIG. 21 is a drawing showing an example of correcting handwritten text line data based on an input field area of ​​a multi-line box type according to one embodiment.

[0184] Referring to FIG. 21, when an input field area (2110) of a multi-line box type corresponding to first handwritten text data (2112) is identified, a processor (220) according to an embodiment may perform a tilt correction (e.g., a second tilt correction) to horizontally align each letter of the first handwritten text line data (2112) according to a reference line corresponding to the letters of the first handwritten text line data (2112) at the location of the first handwritten text line data (2112) according to a multi-line box type correction method, and may correct the size of the first handwritten text line data (2112) or the size of a stroke of the first handwritten text line data (2112) so that the tilt-corrected first handwritten text line data (2112) is included within the input field area (2110) of the multi-line box type. In one embodiment, the processor (220) may perform a tilt correction (e.g., second tilt correction) to horizontally align each letter of the second handwritten text line data (2114) according to a reference line corresponding to the letters of the second handwritten text line data (2114) at the position of the second handwritten text line data (2114) according to a multi-line box type correction method when an input field area (2110) of a multi-line box type corresponding to the second handwritten text line data (2114) is identified, and may correct the size of the second handwritten text line data (2114) or the size of a stroke of the second handwritten text line data (2114) so ​​that the tilt-corrected second handwritten text line data (2114) is included in the input field area (2110) of the multi-line box type.According to one embodiment, a processor (220) may perform line spacing correction to correct a line spacing between the corrected first handwritten text line data (2122) and the corrected second handwritten text line data (2124) so ​​that the corrected first handwritten text line data (2112) and the corrected second handwritten text line data (2124) have a specified line spacing (2125) after correcting the input field area (2110) of a multi-line box type to include first handwritten text line data (2112) and second handwritten text line data (2114).

[0185] FIG. 22 is a drawing showing a character using a descent region according to one embodiment.

[0186] Referring to FIG. 22, a processor (220) according to an embodiment may identify, through document analysis, whether handwritten text data includes characters (2212) (e.g., alphabets) that use a descent region (2220). For example, the descent region (2220) may be an area below a baseline (2210) in which at least a portion (e.g., a descender) of a character (e.g., a j) is represented. Characters that use the descent region (2220) according to an embodiment may include Latin characters.

[0187] FIG. 23 is a diagram showing an example of correction when handwritten text line data includes characters using a descent region according to one embodiment.

[0188] Referring to FIG. 23, a processor (220) according to an embodiment identifies an input field area (2310) of an underscore type corresponding to handwritten text line data (2312) and, if the handwritten text line data (2312) includes a character having a descender portion (e.g., a portion that should be placed below the baseline in q), performs a slope correction (e.g., a third slope correction) to horizontally place each character (quick) of the handwritten text line data (2312) along an under line (2301) corresponding to the input field area (2310) of the underscore type according to a correction method based on the underscore type, and adjusts the position of the slope-corrected handwritten text line data (2312) or the slope-corrected handwritten text line data (2312) so that the descender portion of the characters of the slope-corrected handwritten text line data (2312) is placed below the under line (2301). Correction can be made to move the positions of strokes. In one embodiment, corrected handwritten text line data (2322) can be displayed so that the descender portions of the letters of the tilt-corrected handwritten text line data (2312) are positioned below the underline (2301).

[0189] FIG. 24 is a flowchart illustrating a handwriting correction operation based on a background input field according to a candidate correction request according to one embodiment.

[0190] Referring to FIG. 24, a processor (e.g., processor (120) of FIG. 1 or processor (220) of FIG. 2, hereinafter, processor (220) of FIG. 2 will be described as an example) of an electronic device (e.g., electronic device (101) of FIG. 1 or electronic device (201) of FIG. 2) according to one embodiment may perform at least one operation from operations 2412 to 2428.

[0191] In operation 2412, the processor (220) according to one embodiment may identify a handwriting selection area based on a user input. The processor (220) according to one embodiment may identify a handwriting selection area based on a user input designating a handwriting selection area after handwriting input on an application screen (e.g., a note application screen or a designated page).

[0192] In operation 2414, the processor (220) according to one embodiment may collect handwriting data strokes within a handwriting selection area. For example, the processor (220) may collect handwriting data strokes already entered into the handwriting selection area.

[0193] In operation 2416, the processor (220) according to one embodiment may identify whether a background image exists within the handwriting selection area. For example, the processor (220) may identify whether a file or data other than handwriting is displayed on the lowest layer (or background) corresponding to the handwriting selection area. For example, the file or data may include a document file (e.g., a portable document format (PDF) file), a file including a document form such as a contract, a report, meeting minutes, a question paper, a note, or a teaching material, or an image file.

[0194] In operation 2418, the processor (220) according to one embodiment may identify a page (e.g., the entire screen or the entire handwriting input area) as an input field area if no background image exists within the handwriting selection area.

[0195] In operation 2420, the processor (220) according to an embodiment may correct handwritten text line data within a handwriting selection area using a specified correction method based on an input field area corresponding to a page. The processor (220) according to an embodiment may correct handwritten text line data using a specified correction method (e.g., a basic correction method) regardless of the input field area when the input field area is identified as a page. According to an embodiment, the basic correction method may include some or all of a plurality of corrections. For example, the plurality of corrections may include line tilt correction, line spacing correction, word spacing correction, letter correction, and / or slant correction. For example, line tilt correction may be a correction that analyzes each stroke segment of characters of the handwritten text line data to identify reference positions, identifies a line (e.g., a reference line) corresponding to the reference positions, and horizontalizes characters of the handwritten text line data according to the reference line. Line spacing correction may be a correction that allows handwritten text line data to be included in the space between the top line and the bottom line, while being spaced apart from the top line and the bottom line by a certain space (or interval). Word spacing correction may be a correction that allows the space (or interval) between words in the handwritten text line data to be certain. Letter correction may be a correction that removes unintended serif portions from each letter in the handwritten text line data. Slant correction may be a correction that removes slant from letters. According to an embodiment, the processor (220) may provide an option that allows selection of whether to apply each of a plurality of corrections of a basic correction method, and may activate some or all of the plurality of corrections based on a user selection input through the option.

[0196] In operation 2422, the processor (220) according to one embodiment may identify whether an input field area exists in a background image area corresponding to the handwriting selection area if a background image for the handwriting selection area exists. The processor (220) according to one embodiment may determine at least one input field area of ​​the background image area based on a shape indicated by at least one pass of the background image area. For example, if a box shape is identified by at least one pass of the background image area, the processor (220) may identify an input field area corresponding to the box shape. If an underline shape is identified by at least one pass of the background image area, the processor (220) may identify an input field area corresponding to the underline shape. If a bracket shape is identified by at least one pass of the background image area, the processor (220) may identify an input field area corresponding to the bracket shape. According to an embodiment, the processor (220) may determine (or identify) at least one input field area based on input field area information provided for a background image area, if any. For example, if the background image includes a file (e.g., a PDF file) that provides input field information, the processor (220) may receive input field area information included in the file of the background image to determine the input field area of ​​the background image area. According to an embodiment, the processor (220) may determine the bounds of each of at least one input field area based on the font size of text existing within a specified distance from each of at least one input field areas.For example, when an underscore type input field area is identified and text information of text within a specified distance from the underscore type input field area is obtained, the processor (220) may determine the bounds of the underscore type input field area so that the vertical length (or height) of the underscore type input field area is longer (or higher) than the vertical length (or height) of the font based on the font of the characters included in the text. For example, when a parenthesis type input field area is identified and text information of text within a specified distance from the parenthesis type input field area is obtained, the processor (220) may determine the bounds of the parenthesis type input field area so that the vertical length (or height) of the parenthesis type input field area is longer (or higher) than the vertical length (or height) of the font based on the font of the characters included in the text. According to one embodiment, the processor (220) may perform operations 2418 and 2420 if there is no input field area in the background image area corresponding to the handwriting selection area. According to one embodiment, the processor (220) may perform operation 2424 if there is at least one input field area in the background image area corresponding to the handwriting selection area.

[0197] In operation 2424, the processor (220) according to an embodiment may match at least one input field area within a handwriting selection area with handwriting text line data. The processor (220) according to an embodiment may compare the bound information of the handwriting text line data within the handwriting selection area with the bound of the input field area within the handwriting selection area, and if there is an input field area overlapping with the handwriting text line data, the processor (220) may identify the input field area overlapping with the handwriting text line data as an input field area corresponding to the handwriting text line data. If there are multiple input field areas overlapping with the handwriting text line data, the processor (220) according to an embodiment may identify (or determine or select) the input field area with the widest overlapping range as the input field area corresponding to the handwriting text line data.

[0198] In operation 2426, the processor (220) according to one embodiment may correct the handwritten text line data to be included in an input field area corresponding to the handwritten text line data.

[0199] According to an embodiment, the processor (220) may identify the type of an input field area corresponding to handwritten text line data based on an input field type determination condition, and may correct the handwritten text data to be included in the input field area according to a correction method based on the identified type. For example, the input field type determination condition may include a shape of the input field area, a horizontal length of the input field area, a vertical length of the input field area, a ratio of the horizontal length and the vertical length of the input field area, and / or a number of text lines corresponding to the input field area. According to an embodiment, the processor (220) may identify the type of the input field area corresponding to the handwritten text line data as one of a first type (e.g., unclassified type), a second type (e.g., single-line box type), a third type (e.g., multi-line box type), a fourth type (e.g., check box type), a fifth type (e.g., underscore type), or a sixth type (e.g., parentheses type) based on the input field type determination condition. According to one embodiment, the processor (220) may correct the slope, size, and / or stroke of the handwritten text line data so that the handwritten text line data is included in the input field area of ​​the unclassified type based on bound information (e.g., layout information) of the input field area provided from the background image, if the type of the input field area corresponding to the handwritten text line data is an unclassified type.

[0200] In one embodiment, the processor (220) performs a tilt correction (e.g., a first tilt correction) to horizontally level each character of the handwritten text line data along a bottom line of the input field area of ​​the single-line box type when the type of the input field area corresponding to the handwritten text line data is a single-line box type, and corrects the size of the handwritten text line data tilt-corrected along the bottom line (e.g., a reduction correction) so that the handwritten text line data tilt-corrected along the bottom line is included in the input field area of ​​the single-line box type, or corrects the sizes of strokes included in the handwritten text line data (e.g., a reduction correction).

[0201] According to an embodiment, if the type of the input field area corresponding to the handwritten text line data is a multi-line box type, the processor (220) may perform a tilt correction (e.g., a second tilt correction) to horizontally align each character of the handwritten text line data according to a reference line according to a reference position corresponding to the characters of the handwritten text line data, and may correct the size of the corrected handwritten text line data (e.g., reduction) so that the corrected handwritten text line data is included in the input field area of ​​the multi-line box type, or may correct the sizes of strokes included in the corrected handwritten text line data (e.g., reduction correction). In an embodiment, when the type of the input field area corresponding to handwritten text line data is a multi-line box type and a plurality of handwritten text line data (e.g., first handwritten text line data and second handwritten text line data) exist, the processor (220) may correct each of the first and second handwritten text line data using a multi-line box type correction method, and then perform line spacing correction so that the first handwritten text line data and the second handwritten text line data have a constant line spacing (line space). For example, the length of the line spacing may be determined within a range in which the first and second handwritten text line data do not exceed the input field area of ​​the multi-line box type, and may be set to the length of the line spacing of texts within a specified distance from the input field area of ​​the multi-box type.

[0202] In one embodiment, the processor (220) may identify whether the handwritten text data includes a character (e.g., an alphabet) having a descender if the type of the input field area corresponding to the handwritten text line data is an underscore type. For example, a descender may be a portion of an alphabet where a letter of a font extends below a baseline. In one embodiment, the processor (220) may perform a slope correction (e.g., a third slope correction) to horizontalize each character of the handwritten text line data according to the underline of the input field area of ​​the underscore type if the type of the input field area corresponding to the handwritten text line data is an underscore type and the handwritten text data does not include a character having a descender, and may correct the size of the corrected handwritten text line data (e.g., a reduction correction) so that the handwritten text line data that has been slope-corrected according to the underline is included in the input field area of ​​the underscore type, or may correct the sizes of strokes included in the handwritten text line data (e.g., a reduction correction).In an embodiment, the processor (220) performs a tilt correction (e.g., a third tilt correction) to horizontally level each character of the handwritten text line data according to the underline of the input field area of ​​the underscore type when the type of the input field area corresponding to the handwritten text line data is an underscore type and the handwritten text data includes characters having descenders, moves the position of the corrected handwritten text line data so that the descender portions of the characters of the corrected handwritten text line data are placed below the underline, or performs a correction to move the positions of the strokes included in the handwritten text line data, and corrects the size of the corrected handwritten text line data (e.g., a reduction correction) so that the corrected handwritten text line data is included in the input field area of ​​the underscore type or corrects the sizes of the strokes included in the handwritten text line data (e.g., a reduction correction).

[0203] In operation 2428, the processor (220) according to one embodiment may display the corrected handwritten text line data. The processor (220) according to one embodiment may display the corrected handwritten text line data so that the handwritten text line data is included in the input field area according to a correction method based on a specified basic correction method or a type of input field area corresponding to (matching) the handwritten text line data.

[0204] FIG. 25 is a drawing showing an example of a handwriting correction screen based on an input field of a background during candidate correction according to one embodiment.

[0205] Referring to FIG. 25, a processor (220) according to an embodiment may display an application screen (2500) (e.g., a note application) for handwriting correction based on an input field of a background. The processor (220) according to an embodiment may display various function menus and a page (2510) including a post-correction menu (2501) and an automatic correction menu (2502) on the application screen (2500). The processor (220) according to an embodiment may receive handwriting input through the page (2510) and display the received handwriting data (2512). In one embodiment, the processor (220) may identify the handwriting selection area when a user input designating a handwriting selection area is received on a page (2510) and a post-correction menu (2501) is selected, and may correct handwriting text line data of the handwriting selection area using a default correction method or a correction method based on a type of an input field area corresponding to the handwriting text line data so that the handwriting text line data is included within the input field area. In one embodiment, the processor (220) may display a handwriting text line data correction menu screen (2503) (e.g., handwriting alignment) that may activate or deactivate at least some or all of the corrections of the default correction methods for the handwriting text line data. For example, the handwritten text line data correction menu screen (2503) may include a horizontal alignment item corresponding to line tilt correction, a line alignment item corresponding to line spacing correction, a word spacing alignment item corresponding to word spacing correction, and a character shape correction item corresponding to letter correction and / or slant correction.

[0206] FIG. 26 is a flowchart illustrating a handwriting correction operation based on an input field of a background according to an automatic correction request according to one embodiment.

[0207] Referring to FIG. 26, a processor (e.g., processor (120) of FIG. 1 or processor (220) of FIG. 2, hereinafter, processor (220) of FIG. 2 will be described as an example) of an electronic device (e.g., electronic device (101) of FIG. 1 or electronic device (201) of FIG. 2) according to one embodiment may perform at least one operation from operations 2612 to 2628.

[0208] In operation 2612, a processor (220) according to an embodiment may collect and store handwriting data strokes according to handwriting input, and correct (e.g., letter correction) letters corresponding to the handwriting data strokes at time units based on a timer associated with automatic correction (or real-time correction). For example, real-time correction may be performed based on the completion of a word according to the input handwriting. For example, real-time correction may be a method in which a first word is input, and when a second word is input, correction is performed for the first word at the time of inputting the second word. For example, real-time correction may be a method in which input handwriting is automatically corrected when a specified time has elapsed after the user inputs handwriting.

[0209] In operation 2614, the processor (220) according to an embodiment may determine whether handwritten text line data is identifiable using the collected handwritten data strokes. The processor (220) according to an embodiment may classify the collected strokes into strokes of a handwritten text group and strokes of a handwritten non-text data group through document analyzing of the collected handwritten data strokes, and determine whether at least one handwritten text line data corresponding to the strokes of the handwritten text group exists.

[0210] In operation 2616, the processor (220) according to one embodiment may identify whether a background image exists when handwritten text line data corresponding to the collected handwritten data strokes is identified. For example, the processor (220) may identify whether a file or data that serves as the background of the handwriting is displayed on the lowest layer (or background). For example, the file or data may include a document file (e.g., a portable document format (PDF) file), a file containing a document form such as a contract, a report, meeting minutes, a question paper, a note, or a teaching material, or an image file.

[0211] In operation 2618, the processor (220) according to one embodiment may identify a page (e.g., the entire screen or the entire handwriting input area) as an input field area if no background image exists.

[0212] In operation 2620, the processor (220) according to an embodiment may correct handwritten text line data using a specified correction method based on an input field area corresponding to a page. The processor (220) according to an embodiment may correct handwritten text line data using a specified correction method (e.g., a basic correction method) regardless of the input field area when the input field area is identified as a page. According to an embodiment, the basic correction method may include a plurality of corrections. According to an embodiment, the basic correction method may include some or all of the plurality of corrections. For example, the plurality of corrections may include line slant correction, line spacing correction, word spacing correction, letter correction, and / or slant correction. For example, line slant correction may be a correction that analyzes the stroke segments of each character of handwritten text line data to identify reference positions, identifies lines (e.g., reference lines) corresponding to the reference positions, and horizontalizes characters of the handwritten text line data according to the reference lines. Line spacing correction may be a correction that includes the handwritten text line data in the space between the top line and the bottom line, while being spaced apart from each of the top line and the bottom line by a constant space (or interval). Word spacing correction may be a correction that makes the space (or interval) between words of the handwritten text line data constant. Letter correction may be a correction that removes unintended serif portions from each character of the handwritten text line data. Slant correction may be a correction that removes slant from characters. According to an embodiment, the processor (220) may provide an option that allows selection of whether to apply each of a plurality of corrections of a basic correction method, and may activate some or all of the plurality of corrections based on a user selection input through the option.

[0213] In operation 2422, the processor (220) according to one embodiment may identify whether an input field area exists in the background image if a background image exists. The processor (220) according to one embodiment may determine at least one input field area of ​​the background image based on a shape indicated by at least one pass of the background image. For example, if a box shape is identified by at least one pass of the background image, the processor (220) may identify an input field area corresponding to the box shape. If an underline shape is identified by at least one pass of the background image, the processor (220) may identify an input field area corresponding to the underline shape. If a bracket shape is identified by at least one pass of the background image, the processor (220) may identify an input field area corresponding to the bracket shape. If input field area information provided for the background image exists, the processor (220) according to one embodiment may determine (or identify) at least one input field area based on input field area information. For example, if the background image includes a file (e.g., a PDF file) that provides input field information, the processor (220) may determine the input field area of ​​the background image by receiving input field area information included in the file of the background image. In one embodiment, the processor (220) may determine the bounds of each of at least one input field area based on the font size of text present within a specified distance from each of at least one input field areas.For example, if an underscore type input field area is identified and text information of text within a specified distance from the underscore type input field area is obtained, the processor (220) may determine the bounds of the underscore type input field area so that the vertical length (or height) of the underscore type input field area is longer (or higher) than the vertical length (or height) of the font based on the font of the characters included in the text. For example, if a parenthesis type input field area is identified and text information of text within a specified distance from the parenthesis type input field area is obtained, the processor (220) may determine the bounds of the parenthesis type input field area so that the vertical length (or height) of the parenthesis type input field area is longer (or higher) than the vertical length (or height) of the font based on the font of the characters included in the text. In one embodiment, the processor (220) may perform operation 2618 if the input field area does not exist in the background image. According to one embodiment, the processor (220) may perform operation 2624 if at least one input field area exists in the background image area.

[0214] In operation 2624, the processor (220) according to an embodiment may match an input field area with handwritten text line data. The processor (220) according to an embodiment may compare the bound information of the handwritten text line data with the bound of at least one input field area, and if there is an input field area overlapping with the handwritten text line data, the processor (220) may identify the input field area overlapping with the handwritten text line data as an input field area corresponding to the handwritten text line data. If there are multiple input field areas overlapping with the handwritten text line data, the processor (220) according to an embodiment may identify (or determine or select) the input field area with the widest overlapping range as the input field area corresponding to the handwritten text line data.

[0215] In operation 2626, the processor (220) according to one embodiment may correct the handwritten text line data to be included in an input field area corresponding to the handwritten text line data.

[0216] According to an embodiment, the processor (220) may identify the type of an input field area corresponding to handwritten text line data based on an input field type determination condition, and may correct the handwritten text data to be included in the input field area according to a correction method based on the identified type. For example, the input field type determination condition may include a shape of the input field area, a horizontal length of the input field area, a vertical length of the input field area, a ratio of the horizontal length and the vertical length of the input field area, and / or a number of text lines corresponding to the input field area. According to an embodiment, the processor (220) may identify the type of the input field area corresponding to the handwritten text line data as one of a first type (e.g., unclassified type), a second type (e.g., single-line box type), a third type (e.g., multi-line box type), a fourth type (e.g., check box type), a fifth type (e.g., underscore type), or a sixth type (e.g., parentheses type) based on the input field type determination condition. According to one embodiment, the processor (220) may correct the slope, size, and / or stroke of the handwritten text line data so that the handwritten text line data is included in the input field area of ​​the unclassified type based on bound information (e.g., layout information) of the input field area provided from the background image, if the type of the input field area corresponding to the handwritten text line data is an unclassified type.

[0217] In one embodiment, the processor (220) performs a tilt correction (e.g., a first tilt correction) to horizontally level each character of the handwritten text line data along a bottom line of the input field area of ​​the single-line box type when the type of the input field area corresponding to the handwritten text line data is a single-line box type, and corrects the size of the handwritten text line data tilt-corrected along the bottom line (e.g., a reduction correction) so that the handwritten text line data tilt-corrected along the bottom line is included in the input field area of ​​the single-line box type, or corrects the sizes of strokes included in the handwritten text line data (e.g., a reduction correction).

[0218] According to an embodiment, if the type of the input field area corresponding to the handwritten text line data is a multi-line box type, the processor (220) may perform a tilt correction (e.g., a second tilt correction) to horizontally align each character of the handwritten text line data according to a reference line according to a reference position corresponding to the characters of the handwritten text line data, and may correct the size of the corrected handwritten text line data (e.g., reduction) so that the corrected handwritten text line data is included in the input field area of ​​the multi-line box type, or may correct the sizes of strokes included in the corrected handwritten text line data (e.g., reduction correction). In an embodiment, when the type of the input field area corresponding to handwritten text line data is a multi-line box type and a plurality of handwritten text line data (e.g., first handwritten text line data and second handwritten text line data) exist, the processor (220) may correct each of the first and second handwritten text line data using a multi-line box type correction method, and then perform line spacing correction so that the first handwritten text line data and the second handwritten text line data have a constant line spacing (line space). For example, the length of the line spacing may be determined within a range in which the first and second handwritten text line data do not exceed the input field area of ​​the multi-line box type, and may be set to the length of the line spacing of texts within a specified distance from the input field area of ​​the multi-box type.

[0219] In one embodiment, the processor (220) may identify whether the handwritten text data includes a character (e.g., an alphabet) having a descender if the type of the input field area corresponding to the handwritten text line data is an underscore type. For example, a descender may be a portion of an alphabet where a letter of a font extends below a baseline. In one embodiment, the processor (220) may perform a slope correction (e.g., a third slope correction) to horizontalize each character of the handwritten text line data according to the underline of the input field area of ​​the underscore type if the type of the input field area corresponding to the handwritten text line data is an underscore type and the handwritten text data does not include a character having a descender, and may correct the size of the corrected handwritten text line data (e.g., a reduction correction) so that the handwritten text line data that has been slope-corrected according to the underline is included in the input field area of ​​the underscore type, or may correct the sizes of strokes included in the handwritten text line data (e.g., a reduction correction).In an embodiment, the processor (220) performs a tilt correction (e.g., a third tilt correction) to horizontally level each character of the handwritten text line data according to the underline of the input field area of ​​the underscore type when the type of the input field area corresponding to the handwritten text line data is an underscore type and the handwritten text data includes characters having descenders, moves the position of the corrected handwritten text line data so that the descender portions of the characters of the corrected handwritten text line data are placed below the underline, or performs a correction to move the positions of the strokes included in the handwritten text line data, and corrects the size of the corrected handwritten text line data (e.g., a reduction correction) so that the corrected handwritten text line data is included in the input field area of ​​the underscore type or corrects the sizes of the strokes included in the handwritten text line data (e.g., a reduction correction).

[0220] In operation 2628, the processor (220) according to one embodiment may display corrected handwritten text data. The processor (220) according to one embodiment may display corrected handwritten text data such that the handwritten text line data is included in the input field area according to a correction method based on a specified basic correction method or a type of input field area corresponding to (matching) the handwritten text line data.

[0221] FIG. 27 is a drawing showing an example of a handwriting correction screen based on an input field of a background during automatic correction according to one embodiment.

[0222] Referring to FIG. 27, a processor (220) according to an embodiment may display an application screen (2700) (e.g., a note application) for handwriting correction based on an input field of a background. The processor (220) according to an embodiment may display various function menus and a page (2710) including a post-correction menu (2701) and an automatic correction menu (2702) on the application screen (2700). The processor (220) according to an embodiment may receive handwriting input through the page (2710), collect and store handwriting data strokes (2712) according to the handwriting input, and correct letters corresponding to the handwriting data strokes (2712) at time units based on a timer associated with automatic correction when the automatic correction menu (2702) is activated (or on).

[0223] Electronic devices according to the various embodiments disclosed in this document may take various forms. Electronic devices may include, for example, portable communication devices (e.g., smartphones), computer devices, portable multimedia devices, portable medical devices, cameras, wearable devices, or home appliances. Electronic devices according to the embodiments disclosed in this document are not limited to the aforementioned devices.

[0224] The various embodiments of this document and the terminology used therein are not intended to limit the technical features described in this document to specific embodiments, but should be understood to include various modifications, equivalents, or substitutes of the embodiments. In connection with the description of the drawings, similar reference numerals may be used for similar or related components. The singular form of a noun corresponding to an item may include one or more of the items, unless the context clearly indicates otherwise. In this document, each of the phrases "A or B", "at least one of A and B", "at least one of A or B", "A, B, or C", "at least one of A, B, and C", and "at least one of A, B, or C" can include any one of the items listed together in the corresponding phrase among those phrases, or all possible combinations thereof. Terms such as "first," "second," or "first" or "second" may be used merely to distinguish one component from another, and do not limit the components in any other respect (e.g., importance or order). When a component (e.g., a first component) is referred to as "coupled" or "connected" to another (e.g., a second component), with or without the terms "functionally" or "communicatively," it means that the component can be connected to the other component directly (e.g., wired), wirelessly, or through a third component.

[0225] The term "module" used in various embodiments of this document may include a unit implemented in hardware, software, or firmware, and may be used interchangeably with terms such as logic, logic block, component, or circuit. A module may be an integral component, or a minimum unit or part of such a component that performs one or more functions. For example, according to one embodiment, a module may be implemented in the form of an application-specific integrated circuit (ASIC).

[0226] Various embodiments of the present document may be implemented as software (e.g., a program (140)) including one or more commands stored in a storage medium (e.g., an internal memory (136) or an external memory (138)) readable by a machine (e.g., an electronic device (101)). For example, a processor (e.g., a processor (120)) of the machine (e.g., an electronic device (101)) may call at least one command among the one or more commands stored from the storage medium and execute it. This enables the machine to operate to perform at least one function according to the at least one command called. The one or more commands may include code generated by a compiler or code executable by an interpreter. The machine-readable storage medium may be provided in the form of a non-transitory storage medium. Here, 'non-transitory' simply means that the storage medium is a tangible device and does not contain signals (e.g., electromagnetic waves), and the term does not distinguish between cases where data is stored semi-permanently or temporarily on the storage medium.

[0227] In a non-transitory storage medium storing a program of the present disclosure, the program, when executed by at least one processor (e.g., the processor (120) of FIG. 1 or the processor (220) of FIG. 2) of an electronic device (e.g., the electronic device (101) of FIG. 1 or the electronic device (201) of FIG. 2), causes the electronic device to perform the following operations: displaying a background image through a display, and obtaining handwriting text line data using strokes corresponding to handwriting input when handwriting is input on a screen on which the background image is displayed; identifying at least one input field area of ​​the background image based on a shape indicated by at least one path of the background image; determining a bound of each of the at least one input field area based on a font size of text existing within a specified distance from each of the at least one input field area; identifying an input field area corresponding to the handwriting text line data among the at least one input field area based on the bound of each of the at least one input field area; identifying a type of the input field area based on an input field type determination condition; and determining whether the handwriting text line data is input to the input field area. It may include commands set to execute an operation to correct the handwritten text line data according to a correction method based on the identified type so as to be included within the bound.

[0228] According to one embodiment, the method according to various embodiments disclosed in the present document may be provided as a computer program product. The computer program product may be traded between sellers and buyers as a product. The computer program product may be distributed in the form of a device-readable storage medium (e.g., compact disc read-only memory (CD-ROM)) or may be provided through an application store (e.g., Play Store). TM) or directly between two user devices (e.g., smart phones), online distribution (e.g., downloading or uploading). In the case of online distribution, at least a portion of the computer program product may be at least temporarily stored or temporarily created in a machine-readable storage medium, such as the memory of a manufacturer's server, an application store's server, or an intermediary server.

[0229] According to various embodiments, each component (e.g., a module or a program) of the above-described components may include one or more entities, and some of the entities may be separated and placed in other components. According to various embodiments, one or more components or operations of the aforementioned components may be omitted, or one or more other components or operations may be added. Alternatively or additionally, a plurality of components (e.g., a module or a program) may be integrated into a single component. In such a case, the integrated component may perform one or more functions of each of the plurality of components identically or similarly to those performed by the corresponding component among the plurality of components prior to the integration. According to various embodiments, the operations performed by a module, program, or other component may be executed sequentially, in parallel, iteratively, or heuristically, or one or more of the operations may be executed in a different order, omitted, or one or more other operations may be added.

[0230] Although the embodiments have been described with limited examples and drawings, those skilled in the art will appreciate that various modifications and variations can be made based on the above teachings. For example, appropriate results can be achieved even if the described techniques are performed in a different order than described, and / or components of the described systems, structures, devices, circuits, etc. are combined or combined in a different manner than described, or are replaced or substituted with other components or equivalents. Therefore, other implementations, other embodiments, and equivalents of the claims also fall within the scope of the claims described below.

Claims

1. In the electronic device (101, 201), A display (160, 260) including a touch panel; Memory (130, 230) for storing instructions; and Contains at least one processor (120, 220), The above instructions, when individually or collectively executed by the at least one processor, cause the electronic device to: Display the background image through the above display, When handwriting is input on a screen where the above background image is displayed, handwriting text line data is obtained using strokes corresponding to the handwriting input, Identifying at least one input field area of ​​the background image based on a shape represented by at least one pass of the background image, Determine the bounds of each of the at least one input field area based on the font size of text existing within a specified distance from each of the at least one input field areas, Identifying an input field area corresponding to the handwritten text line data among the at least one input field area based on the bounds of each of the at least one input field area, Identifying the type of the input field area based on the input field type judgment condition, and An electronic device that corrects the handwritten text line data according to a correction method based on the identified type so that the handwritten text line data is included within the bounds of the input field area.

2. In paragraph 1, The above input field type determination conditions include an electronic device including the shape of the input field area, the horizontal length of the input field area, the vertical length of the input field area, the ratio of the horizontal length and the vertical length of the input field area, and / or the number of text lines corresponding to the input field area.

3. In paragraph 1 or 2, The above instructions, when individually or collectively executed by the at least one processor, cause the electronic device to: An electronic device that identifies the type of the input field area corresponding to the handwritten text line data as one of an unclassified type, a single-line box type, a multi-line box type, a check box type, an underscore type, or a parenthesis type based on the input field type judgment condition.

4. In any one of paragraphs 1 to 3, The above instructions, when individually or collectively executed by the at least one processor, cause the electronic device to: An electronic device that performs a correction to horizontally align each character of the handwritten text line data according to a single-line box type correction method in the case where the identified type is the single-line box type, and corrects the size of the corrected handwritten text line data or the size of strokes of the corrected handwritten text line data so that the corrected handwritten text line data is included in the input field area of ​​the single-line box type.

5. In any one of paragraphs 1 to 4, The above instructions, when individually or collectively executed by the at least one processor, cause the electronic device to: An electronic device that performs a correction to horizontally align each character of the handwritten text line data according to a reference line corresponding to the characters of the handwritten text line data according to a multi-line box type correction method when the identified type is the multi-line box type, and corrects the size of the corrected handwritten text line data or the size of the strokes of the corrected handwritten text line data so that the corrected handwritten text line data is included within an input field area of ​​the multi-line box type.

6. In any one of paragraphs 1 to 5, The above instructions, when individually or collectively executed by the at least one processor, cause the electronic device to: An electronic device for correcting the first handwritten text line data and the second handwritten text line data according to a correction method based on the multi-line box type, when the identified type is the multi-line box type and the first handwritten text line data and the second handwritten text line data correspond to an input field area of ​​the multi-line box type, and correcting the line spacing between the corrected first handwritten text line data and the corrected second handwritten text line data to become a specified line spacing.

7. In any one of paragraphs 1 to 6, The above instructions, when individually or collectively executed by the at least one processor, cause the electronic device to: An electronic device for performing a correction so that each character of the handwritten text line data is horizontally aligned along an underline of an input field area of ​​the underscore type according to a correction method based on the underscore type when the identified type is the underscore type and the handwritten text data includes characters having the descender portion, and performing a correction so as to move a position of the corrected handwritten text line data or a position of strokes included in the corrected handwritten text line data so that the descender portion of the characters of the corrected handwritten text line data is positioned below the underline.

8. In any one of paragraphs 1 to 7, The above instructions, when individually or collectively executed by the at least one processor, cause the electronic device to: If an input field area corresponding to the handwritten text line data among the at least one input field area is not identified, the handwritten text line data is corrected based on a basic correction method, An electronic device wherein the above basic correction method includes line slope correction, line spacing correction, word spacing correction, letter correction and / or bevel correction.

9. In any one of paragraphs 1 to 8, The above instructions, when individually or collectively executed by the at least one processor, cause the electronic device to: Performing document analyzing on the strokes corresponding to the above handwriting input to obtain text group data and non-text group data from the strokes corresponding to the above handwriting input, and An electronic device that performs text recognition on the above text group data to obtain the handwritten text line data.

10. In a handwriting correction method based on an input field of a background in an electronic device (101, 201), An action of displaying a background image through the display of the electronic device; An action of obtaining handwritten text line data by using strokes corresponding to handwritten input when handwriting is input on a screen on which the above background image is displayed; An operation of identifying at least one input field area of ​​the background image based on a shape represented by at least one pass of the background image; An operation of determining a bound of each of said at least one input field area based on a font size of text existing within a specified distance from each of said at least one input field area; An operation of identifying an input field area corresponding to the handwritten text line data among the at least one input field area based on the bounds of each of the at least one input field area; An operation for identifying the type of the input field area based on an input field type judgment condition; and A method comprising an action of correcting the handwritten text line data according to a correction method based on the identified type so that the handwritten text line data is included within the bounds of the input field area.

11. In paragraph 10, The above input field type judgment conditions include the shape of the input field area, the horizontal length of the input field area, the vertical length of the input field area, the ratio of the horizontal length and vertical length of the input field area, and / or the number of text lines corresponding to the input field area. A method including an action of identifying the type of the input field area corresponding to the handwritten text line data as one of an unclassified type, a single-line box type, a multi-line box type, a check box type, an underscore type, or a parenthesis type based on the input field type judgment condition.

12. In paragraph 10 or 11, A method comprising: performing a correction to horizontally align each character of the handwritten text line data according to a single-line box type correction method in a case where the identified type is the single-line box type; and correcting the size of the corrected handwritten text line data or the size of strokes of the corrected handwritten text line data so that the corrected handwritten text line data is included in the input field area of ​​the single-line box type.

13. In any one of paragraphs 10 to 12, A method comprising: performing a correction to horizontally align each character of the handwritten text line data according to a reference line corresponding to the characters of the handwritten text line data according to a multi-line box type correction method when the identified type is the multi-line box type; and correcting the size of the corrected handwritten text line data or the size of strokes of the corrected handwritten text line data so that the corrected handwritten text line data is included within the input field area of ​​the multi-line box type.

14. In any one of paragraphs 10 to 13, An operation of correcting the first handwritten text line data and the second handwritten text line data according to a correction method based on the multi-line box type, when the identified type is the multi-line box type and the first handwritten text line data and the second handwritten text line data correspond to an input field area of ​​the multi-line box type, and correcting the line spacing between the corrected first handwritten text line data and the corrected second handwritten text line data to have a designated line spacing; or A method comprising: performing a correction to horizontally align each character of the handwritten text line data along an underline of an input field area of ​​the underscore type according to a correction method based on the underscore type when the identified type is the underscore type and the handwritten text data includes characters having the descender portion; and performing a correction to move a position of the corrected handwritten text line data or a position of strokes included in the corrected handwritten text line data so that the descender portion of the characters of the corrected handwritten text line data is placed below the underline.

15. In a non-transitory storage medium storing a program, the program, when executed by at least one processor (120, 220) of an electronic device (101, 201), causes the electronic device to: The action of displaying a background image through the display, An action of obtaining handwritten text line data by using strokes corresponding to handwritten input when handwriting is input on a screen where the above background image is displayed; An operation of identifying at least one input field area of ​​the background image based on a shape represented by at least one pass of the background image; An operation of determining a bound of each of said at least one input field area based on a font size of text existing within a specified distance from each of said at least one input field area; An operation of identifying an input field area corresponding to the handwritten text line data among the at least one input field area based on the bounds of each of the at least one input field area; An operation for identifying the type of the input field area based on an input field type judgment condition; and A non-transitory storage medium comprising commands set to execute an operation of correcting the handwritten text line data according to a correction method based on the identified type so that the handwritten text line data is included within the bounds of the input field area.

Images